Trust Assessment
hotel-finder received a trust score of 42/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 4 findings: 1 critical, 1 high, 2 medium, and 0 low severity. Key findings include File read + network send exfiltration, Sensitive path access: AI agent config, Unpinned repository in installation instructions.
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 | |
|---|---|---|---|---|
| CRITICAL | File read + network send exfiltration AI agent config/credential 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/barneyjm/hotel-finder/SKILL.md:41 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/barneyjm/hotel-finder/SKILL.md:41 | |
| MEDIUM | Unpinned repository in installation instructions The installation instructions recommend installing skills directly from a GitHub repository ('https://github.com/barneyjm/camino-skills') without specifying a branch, tag, or commit hash. This means the installation will always pull the latest version from the default branch, which introduces a supply chain risk. If the repository is compromised or a malicious change is introduced, users could unknowingly install and execute compromised code. Recommend pinning the repository to a specific commit hash, tag, or branch (e.g., 'npx skills add https://github.com/barneyjm/camino-skills#v1.0.0' or '#<commit_hash>') to ensure deterministic and secure installations. | LLM | SKILL.md:9 | |
| MEDIUM | Unpinned dependency in installation instructions The installation instructions recommend using 'npx clawhub@latest', which does not pin the version of the 'clawhub' package. This introduces a supply chain risk, as a compromised or malicious future version of 'clawhub' could be installed and executed without explicit user consent, leading to potential arbitrary code execution during skill installation. Recommend pinning the version of 'clawhub' (e.g., 'npx clawhub@1.2.3 install hotel-finder') to mitigate supply chain risks. | LLM | SKILL.md:17 |
Scan History
Embed Code
[](https://skillshield.io/report/28bcba7689203e24)
Powered by SkillShield