Trust Assessment
self-improvement received a trust score of 94/100, 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 Path Traversal via --output-dir in skill extraction script.
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 13, 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 | Path Traversal via --output-dir in skill extraction script The `extract-skill.sh` script allows overriding the `SKILLS_DIR` via the `--output-dir` command-line argument. The script does not sanitize or validate the provided `SKILLS_DIR` value for path traversal sequences (e.g., `../`). An attacker could specify a path like `../../../../tmp` to create directories and write the `SKILL.md` file outside the intended `skills` directory, potentially into sensitive locations. While the `skill-name` itself is validated, the base output directory is not. Sanitize the `--output-dir` argument to prevent path traversal. Ensure the provided path is canonicalized and restricted to an allowed base directory. For example, resolve the path and check if it remains within the expected `skills` directory or a designated safe area before proceeding with file operations. | LLM | scripts/extract-skill.sh:63 |
Scan History
Embed Code
[](https://skillshield.io/report/67c8f11d448033ee)
Powered by SkillShield