find-docs
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the third-party package 'ctx7' globally using 'npm install -g' or execute it via 'npx'. The source is a general package registry and not a verified trusted vendor repository.\n- [COMMAND_EXECUTION]: The skill's operation depends on running shell commands ('ctx7 library' and 'ctx7 docs') to interact with an external documentation service.\n- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection via command injection because it interpolates user-provided library names and queries directly into shell arguments without sanitization or protective boundary markers.\n
- Ingestion points: Library names and search queries provided by the user (found in SKILL.md).\n
- Boundary markers: None. The instructions do not specify any delimiters or safety prompts to prevent the agent from executing shell metacharacters provided in input.\n
- Capability inventory: Access to shell execution to run the 'ctx7' binary (referenced in SKILL.md).\n
- Sanitization: None. There is no logic provided to escape or validate user input before it is passed to the shell.
Audit Metadata