find-docs
Fail
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: HIGHPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains instructions explicitly directing the agent to bypass security boundaries ("Run Context7 CLI requests outside Codex's default sandbox"), which is a direct attempt to override system safety constraints.- [COMMAND_EXECUTION]: The documentation encourages the execution of shell commands through
npxthat are specifically intended to be run outside of restricted execution environments.- [EXTERNAL_DOWNLOADS]: The skill requires the use ofnpx ctx7@latest, which fetches and executes code from the npm registry without verifying the package integrity or source.- [REMOTE_CODE_EXECUTION]: The combination of executing unverified remote packages and instructions to bypass execution sandboxes creates a high risk of arbitrary code execution on the host system.
Recommendations
- AI detected serious security threats
Audit Metadata