Trust Assessment
clawdhub-contributor 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 8 findings: 6 critical, 2 high, 0 medium, and 0 low severity. Key findings include Persistence / self-modification instructions, Arbitrary command execution, File read + network send exfiltration.
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 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings8
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Persistence / self-modification instructions Crontab manipulation (list/remove/edit) Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/starbuck100/clawdhub-contributor/auditor/tests/test_patterns.py:128 | |
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) 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/starbuck100/clawdhub-contributor/auditor/auditor.py:34 | |
| 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/starbuck100/clawdhub-contributor/auditor/tests/test_patterns.py:40 | |
| 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/starbuck100/clawdhub-contributor/auditor/tests/test_patterns.py:43 | |
| 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/starbuck100/clawdhub-contributor/auditor/tests/test_patterns.py:46 | |
| 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/starbuck100/clawdhub-contributor/auditor/tests/test_patterns.py:76 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function '_run_clawdhub'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/starbuck100/clawdhub-contributor/auditor/auditor.py:34 | |
| HIGH | Command Injection in `scout.sh` when checking for required binaries The `scripts/scout.sh` script dynamically checks for the presence of required binaries using `command -v "$bin"`. The `$bin` variable is populated from the `metadata.openclaw.requires.bins` section of a skill's `SKILL.md` frontmatter. If a malicious skill specifies a crafted binary name (e.g., `bash; rm -rf /`), it could lead to arbitrary command execution during the scouting process. Although the current skill's manifest only lists safe binaries (`bash`, `jq`), the `scout.sh` script is designed to analyze *any* skill, making it vulnerable to a malicious `SKILL.md`. Sanitize the `$bin` variable before passing it to `command -v`. Ensure that `$bin` only contains valid, safe executable names. A whitelist approach or strict regex validation (e.g., `^[a-zA-Z0-9_-]+$`) should be applied to each binary name extracted from the `SKILL.md` metadata before it is used in `command -v`. | LLM | scripts/scout.sh:50 |
Scan History
Embed Code
[](https://skillshield.io/report/8b3ca76aec164d71)
Powered by SkillShield