pnpm
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or executable scripts were found. The skill is composed entirely of informational markdown files.
- [SAFE]: Metadata identifies Anthony Fu as the author while the system context specifies fellipeutaka, but the content remains verified documentation.
- [PROMPT_INJECTION]: The skill describes handling project configuration files which represent a surface for indirect prompt injection (Category 8). Evidence Chain: 1. Ingestion points: package.json, pnpm-workspace.yaml, and .pnpmfile.cjs are read to understand project structure. 2. Boundary markers: None identified in the provided documentation examples. 3. Capability inventory: Commands such as pnpm install and pnpm dlx execute lifecycle scripts or remote code. 4. Sanitization: No sanitization of config fields is mentioned in the documentation context.
Audit Metadata