Trust Assessment
get-you-some-britches received a trust score of 90/100, 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, 1 high, 0 medium, and 0 low severity. Key findings include Potential Arbitrary File Read via `filepath` parameter.
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 | |
|---|---|---|---|---|
| HIGH | Potential Arbitrary File Read via `filepath` parameter The `load_results` function in `scripts/aggregate_results.py` accepts a `filepath` argument and reads its content using `json.load()`. If this `filepath` can be influenced by untrusted user input, an attacker could specify paths to sensitive files (e.g., `/etc/passwd`, `/app/config.json`, `/proc/self/environ`) to exfiltrate data from the system. While `json.load` itself is not a command injection vector, reading arbitrary files constitutes a significant data exfiltration risk. Ensure that the `filepath` argument passed to `load_results` is strictly controlled and never directly derived from untrusted user input. If user-controlled input is necessary, implement robust validation to restrict paths to an allow-list of safe files or a tightly sandboxed directory, preventing directory traversal (e.g., `../`). Alternatively, consider passing the file content directly rather than a path if possible. | LLM | scripts/aggregate_results.py:63 |
Scan History
Embed Code
[](https://skillshield.io/report/87ba29e5493995bd)
Powered by SkillShield