library-docs
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- EXTERNAL_DOWNLOADS (LOW): The skill uses
git cloneto download arbitrary repositories from GitHub into the/tmp/cc-reposdirectory. While GitHub is a known platform, the content of individual repositories is unverified and untrusted. - PROMPT_INJECTION (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8). A malicious repository could contain instructions in its README, documentation, or code comments intended to manipulate the 'Explore' subagent's output or actions.
- Ingestion points: Cloned repository content in
/tmp/cc-repos/{repo-name}. - Boundary markers: Absent. The instructions for the subagent do not include delimiters or warnings to ignore embedded instructions within the source code.
- Capability inventory: The skill utilizes
mkdir,ls, andgit clone. The subagent is tasked with reading files and traversing the directory structure. - Sanitization: Absent. The skill does not perform any sanitization or filtering of the cloned content before the subagent processes it.
Audit Metadata