Trust Assessment
test-manager received a trust score of 81/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 4 findings: 0 critical, 0 high, 2 medium, and 2 low severity. Key findings include Unsafe deserialization / dynamic eval, Missing required field: name, Node lockfile missing.
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 Findings4
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/savelieve/test-manager/skill.js:2 | |
| 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/savelieve/test-manager/SKILL.md:1 | |
| LOW | Node lockfile missing package.json is present but no lockfile was found (package-lock.json, pnpm-lock.yaml, or yarn.lock). Commit a lockfile for deterministic dependency resolution. | Dependencies | skills/savelieve/test-manager/package.json | |
| LOW | Filesystem access outside skill directory for configuration The skill reads `TOOLS.md` from a path (`../../../clawd/TOOLS.md`) that is three directories above its own location. While this file is explicitly mentioned in the skill's documentation (`SKILL.md`) as the intended source for credential configuration, accessing files outside the immediate skill package directory represents a broader filesystem scope than strictly necessary for a self-contained skill. This could potentially allow access to other files if the path were less constrained or if the `clawd` directory contained unintended sensitive data. Consider centralizing credential management in a more secure, isolated service or relying solely on environment variables to prevent skills from directly accessing files outside their designated scope. If file access is necessary, ensure the path is as constrained as possible and the target file contains only the intended configuration. | LLM | skill.js:10 |
Scan History
Embed Code
[](https://skillshield.io/report/5b219ca211d1d4a0)
Powered by SkillShield