outdated
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to audit project dependencies.
- Uses
pnpm outdatedto identify available updates. - Uses
pnpm viewto fetch package metadata such as distribution tags, version history, and release timestamps. - [PROMPT_INJECTION]: The skill processes potentially untrusted data from external sources, creating an indirect prompt injection surface.
- Ingestion points: Reads existing migration notes from
tmp/UPGRADES.mdand metadata from the npm registry viapnpmoutputs. - Boundary markers: No specific delimiters are defined to isolate external data from the agent's logic.
- Capability inventory: The skill performs subprocess execution (
pnpm) and file system operations (read/writetmp/UPGRADES.md). - Sanitization: No explicit sanitization or validation of the data retrieved from the registry or the local upgrade file is mentioned.
Audit Metadata