Trust Assessment
llm-models 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 Broad Bash permission for 'infsh' allows arbitrary file access.
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 | Broad Bash permission for 'infsh' allows arbitrary file access The skill declares a broad `Bash(infsh *)` permission, allowing it to execute any command starting with `infsh`. The skill's examples demonstrate the use of `infsh app run ... --input input.json`, which shows that the `infsh` tool can read local files specified by the `--input` argument. If the skill were to construct this `--input` argument from untrusted user input, it could be coerced into reading arbitrary files (e.g., `/etc/passwd`) and potentially exfiltrating their contents by sending them as prompts to external LLMs. While the provided examples do not demonstrate malicious file reading, the declared permission combined with the demonstrated file-reading capability of `infsh` creates a credible data exfiltration vector. Restrict `Bash` permissions to specific `infsh` subcommands and arguments if possible, or ensure all arguments passed to `infsh` are strictly validated and sanitized, especially file paths. If `infsh` has a more granular permission model, use that to limit file access. | LLM | Manifest (frontmatter JSON) |
Scan History
Embed Code
[](https://skillshield.io/report/a1b086256541209a)
Powered by SkillShield