Trust Assessment
clawchat 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 7 findings: 2 critical, 2 high, 3 medium, and 0 low severity. Key findings include Persistence / self-modification instructions, Persistence mechanism: macOS LaunchAgent, Sensitive environment variable access: $HOME.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 55/100, indicating areas for improvement.
Last analyzed on February 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings7
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Persistence / self-modification instructions macOS LaunchAgent/LaunchDaemon persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/alexrudloff/clawchat-p2p/skills/clawchat/SKILL.md:174 | |
| CRITICAL | Arbitrary file read and write due to unsanitized file path from untrusted input The `examples/example-handle-poll-response.sh` script extracts a file path (`POLL_FILE`) directly from an incoming `clawchat` message, which is untrusted input. This path is then used in `cat "$POLL_FILE"` to read file content and `echo "$updated" > "$POLL_FILE"` to write file content. A malicious agent could send a crafted message containing an arbitrary file path (e.g., `/etc/passwd` or `/tmp/malicious_script.sh`), leading to data exfiltration (reading sensitive files) or arbitrary file overwrite/creation. This allows an attacker to read or modify files outside the intended shared directory. Implement strict validation and sanitization of file paths extracted from untrusted input. Paths should be checked against an allowlist of directories, canonicalized, and ensured not to contain any directory traversal sequences (`..`). Instead of directly using the received path, construct a safe, validated path within the intended shared directory. Consider passing data directly in messages rather than relying on shared file paths. | LLM | examples/example-handle-poll-response.sh:13 | |
| HIGH | Persistence mechanism: macOS LaunchAgent Detected macOS LaunchAgent pattern. Persistence mechanisms allow malware to survive system restarts. Review this persistence pattern. Skills should not modify system startup configuration. | Static | skills/alexrudloff/clawchat-p2p/skills/clawchat/SKILL.md:174 | |
| HIGH | Hardcoded and predictable passwords in example scripts Multiple example scripts use hardcoded and predictable passwords (e.g., "secure-password", "example-${agent}-password", "${agent}-secure-2026"). While warnings are present in `SKILL.md` and `scripts/example-multi-agent-setup.sh`, the direct use of such patterns in examples encourages insecure practices and poses a significant risk if adopted in production. An attacker could easily guess or brute-force these credentials.
- Instances include:
- `SKILL.md` (lines 40, 41, 44)
- `examples/example-coordinated-poll.sh` (lines 30, 34)
- `scripts/example-multi-agent-setup.sh` (line 60)
- `examples/example-handle-poll-response.sh` (lines 10, 34) Replace all hardcoded passwords with secure credential management practices (e.g., environment variables, secret management services, or interactive prompts). Ensure example scripts clearly demonstrate *how* to use secure methods, rather than providing insecure defaults. | LLM | scripts/example-multi-agent-setup.sh:60 | |
| 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/alexrudloff/clawchat-p2p/skills/clawchat/examples/example-coordinated-poll.sh:13 | |
| 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/alexrudloff/clawchat-p2p/skills/clawchat/examples/example-handle-poll-response.sh:12 | |
| 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/alexrudloff/clawchat-p2p/skills/clawchat/scripts/example-multi-agent-setup.sh:55 |
Scan History
Embed Code
[](https://skillshield.io/report/d4586e7c18cc282d)
Powered by SkillShield