Trust Assessment
agentvibes-clawbot-tts received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 26 findings: 13 critical, 10 high, 3 medium, and 0 low severity. Key findings include Arbitrary command execution, File read + network send exfiltration, Hidden network beacons / undisclosed telemetry.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, indicating areas for improvement.
Last analyzed on February 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings26
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Remote code download piped to interpreter Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/paulpreibisch/agentvibes-clawbot-tts/SKILL.md:315 | |
| CRITICAL | Arbitrary command execution Remote code download piped to interpreter Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/paulpreibisch/agentvibes-clawbot-tts/setup.sh:304 | |
| CRITICAL | File read + network send exfiltration SSH key/config file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/paulpreibisch/agentvibes-clawbot-tts/SKILL.md:42 | |
| CRITICAL | File read + network send exfiltration SSH key/config file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/paulpreibisch/agentvibes-clawbot-tts/SKILL.md:47 | |
| CRITICAL | File read + network send exfiltration SSH key/config file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/paulpreibisch/agentvibes-clawbot-tts/SKILL.md:56 | |
| CRITICAL | File read + network send exfiltration SSH key/config file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/paulpreibisch/agentvibes-clawbot-tts/SKILL.md:181 | |
| CRITICAL | File read + network send exfiltration SSH key/config file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/paulpreibisch/agentvibes-clawbot-tts/setup.sh:40 | |
| CRITICAL | File read + network send exfiltration SSH key/config file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/paulpreibisch/agentvibes-clawbot-tts/setup.sh:43 | |
| CRITICAL | File read + network send exfiltration SSH key/config file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/paulpreibisch/agentvibes-clawbot-tts/setup.sh:44 | |
| CRITICAL | File read + network send exfiltration SSH key/config file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/paulpreibisch/agentvibes-clawbot-tts/setup.sh:49 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/paulpreibisch/agentvibes-clawbot-tts/SKILL.md:315 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/paulpreibisch/agentvibes-clawbot-tts/setup.sh:304 | |
| CRITICAL | Direct execution of unversioned remote script via curl | bash The skill's `SKILL.md` documentation instructs users to directly download and execute an unversioned shell script from a remote GitHub repository using `curl -sSL ... | bash`. This practice is extremely dangerous as the content of the script can change at any time without notice, potentially introducing malicious code. There is no integrity check or version pinning, making it a critical supply chain vulnerability. An attacker gaining control of the GitHub repository could immediately compromise any system following these instructions. Avoid `curl | bash` for installing software. Instead, provide a package manager installation, a signed installer, or instruct users to download, review, and then execute scripts. If remote execution is necessary, ensure the script is version-locked and has an integrity check (e.g., hash verification). | LLM | SKILL.md:311 | |
| HIGH | Hidden network beacons / undisclosed telemetry Command output piped through base64 encoding Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/paulpreibisch/agentvibes-clawbot-tts/setup.sh:149 | |
| HIGH | Sensitive path access: SSH key/config Access to SSH key/config path detected: '~/.ssh/id_ed25519'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/paulpreibisch/agentvibes-clawbot-tts/SKILL.md:42 | |
| HIGH | Sensitive path access: SSH key/config Access to SSH key/config path detected: '~/.ssh/id_ed25519'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/paulpreibisch/agentvibes-clawbot-tts/SKILL.md:47 | |
| HIGH | Sensitive path access: SSH key/config Access to SSH key/config path detected: '~/.ssh/config'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/paulpreibisch/agentvibes-clawbot-tts/SKILL.md:56 | |
| HIGH | Sensitive path access: SSH key/config Access to SSH key/config path detected: '~/.ssh/config'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/paulpreibisch/agentvibes-clawbot-tts/SKILL.md:181 | |
| HIGH | Sensitive path access: SSH key/config Access to SSH key/config path detected: '~/.ssh/id_ed25519'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/paulpreibisch/agentvibes-clawbot-tts/setup.sh:40 | |
| HIGH | Sensitive path access: SSH key/config Access to SSH key/config path detected: '~/.ssh/id_ed25519'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/paulpreibisch/agentvibes-clawbot-tts/setup.sh:43 | |
| HIGH | Sensitive path access: SSH key/config Access to SSH key/config path detected: '~/.ssh/id_ed25519'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/paulpreibisch/agentvibes-clawbot-tts/setup.sh:44 | |
| HIGH | Sensitive path access: SSH key/config Access to SSH key/config path detected: '~/.ssh/config'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/paulpreibisch/agentvibes-clawbot-tts/setup.sh:49 | |
| HIGH | Unvalidated CLAWDBOT_WORKSPACE leads to command injection in generated script The `setup.sh` script uses the `CLAWDBOT_WORKSPACE` environment variable (aliased as `WORKSPACE`) without proper validation. This variable is then used in a `sed` command to replace a placeholder within the `play-tts.sh` script, which is later executed by Clawdbot. If `CLAWDBOT_WORKSPACE` contains shell metacharacters (e.g., `;`, `$(...)`), these will be expanded when `play-tts.sh` is executed, leading to a command injection vulnerability. For example, setting `CLAWDBOT_WORKSPACE="/tmp/safe; rm -rf /"` could lead to arbitrary command execution. Validate the `CLAWDBOT_WORKSPACE` variable to ensure it only contains safe characters (e.g., alphanumeric, `/`, `_`, `-`, `.`) before using it in file paths or `sed` commands. Alternatively, use `printf %q` or similar shell quoting mechanisms when embedding potentially untrusted strings into other scripts or commands. | LLM | setup.sh:151 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/paulpreibisch/agentvibes-clawbot-tts/SKILL.md:1 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/paulpreibisch/agentvibes-clawbot-tts/setup.sh:19 | |
| MEDIUM | Unpinned npm dependency for `agentvibes` package The `setup.sh` script uses `npm install -g agentvibes` without specifying a version. This means that any time the script is run, it will install the latest version of the `agentvibes` package. If a malicious actor gains control of the `agentvibes` npm package, they could publish a compromised version, which would then be installed and executed by users running this setup script, leading to a supply chain attack. Pin the `agentvibes` dependency to a specific version (e.g., `npm install -g agentvibes@1.0.0`) to ensure reproducibility and prevent unexpected updates or malicious package injections. Consider using a lockfile or a package manager that enforces version pinning. | LLM | setup.sh:70 |
Scan History
Embed Code
[](https://skillshield.io/report/fcc8edb0f7cf7d3a)
Powered by SkillShield