doctor
Pass
Audited by Gen Agent Trust Hub on Jun 2, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's primary function is to instruct the agent to run package installation commands (e.g.,
npm install,pnpm install) and dev servers. This is done to repair dependency drift or missing modules identified during diagnosis. - [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it reads and processes untrusted data, including application source files and external runtime logs (via the
--from-errorand--from-logflags inscripts/check-doctor.mjs). - Ingestion points:
scripts/check-doctor.mjsreads various source file extensions (.js,.jsx,.ts, etc.) and log text provided via CLI arguments. - Boundary markers: None identified in the script or instructions.
- Capability inventory: The skill can modify
package.json, rewrite source code imports, and trigger shell commands via the agent. - Sanitization: The script uses regular expressions to extract specific import patterns but does not sanitize the broader content of the logs or source files it processes.
Audit Metadata