repo-audit
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection. It ingests untrusted data from the repository being audited, including source code, configuration files (e.g., .claude/, CLAUDE.md, AGENTS.md), and the GitHub issue backlog.
- Ingestion points: The skill reads project documentation, source files, and external GitHub issues during Stage 1 and Stage 2.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' prompts when processing the ingested content.
- Capability inventory: The skill has the ability to execute shell commands via external tools (Stage 2) and create persistent project artifacts like epics, PRDs, and GitHub issues (Stage 3 and 4).
- Sanitization: There is no explicit mention of sanitizing or validating the ingested content before it is processed by the analysis personas.
- [EXTERNAL_DOWNLOADS]: The skill utilizes npx, uvx, and pipx to execute standard analysis tools (such as knip, vulture, jscpd, madge, and dependency-cruiser) fetched from well-known public registries like NPM and PyPI.
- [COMMAND_EXECUTION]: The skill executes shell commands to perform repository analysis using various linter and static analysis tools. This is a core part of its functionality for auditing codebases.
Audit Metadata