wiki-qa
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes git commands including 'git remote get-url origin' and 'git rev-parse --abbrev-ref HEAD' to determine the source repository context and branch information.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes arbitrary source code from the repository. Ingestion points: File reading operations during codebase analysis. Boundary markers: No delimiters or ignore instructions are provided to the model when processing file content. Capability inventory: Access to git commands and the local filesystem. Sanitization: The skill does not sanitize or filter content from the source files before processing.
Audit Metadata