Trust Assessment
openclaw-memory-audit received a trust score of 95/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Skill allows scanning arbitrary file system paths.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 12, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Skill allows scanning arbitrary file system paths The `scan_secrets.py` script accepts an optional command-line argument (`sys.argv[1]`) to specify the root directory for scanning. If the agent calls this script with a user-controlled or untrusted path, it could lead to the skill scanning directories outside the intended 'agent workspace and memory logs' scope. This grants the skill excessive read permissions over the file system and could result in the disclosure of sensitive information from unintended locations (Data Exfiltration). While the `SKILL.md` example does not explicitly show an argument being passed, the script's implementation allows for this potential misuse. 1. **Restrict input at agent level**: The agent should ensure that any argument passed to `scan_secrets.py` is either hardcoded to the intended workspace/log directory or strictly validated to prevent path traversal or scanning outside the designated scope. 2. **Internalize path in skill**: Modify the script to always scan a fixed, predefined set of directories (e.g., `os.path.join(os.getcwd(), "workspace")`, `os.path.join(os.getcwd(), "logs")`) instead of accepting an arbitrary `root_dir` from `sys.argv`. If flexibility is absolutely needed, implement strict sanitization and validation of the input path within the script itself to ensure it remains within authorized boundaries. | LLM | scripts/scan_secrets.py:50 |
Scan History
Embed Code
[](https://skillshield.io/report/06a3704a3eb502ca)
Powered by SkillShield