repo-organization-audit
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection because it reads and processes untrusted content from various repository files, such as source code, READMEs, and configurations. This surface could be exploited if an attacker embeds malicious instructions within those files to manipulate the agent's findings or cleanup suggestions.
- Ingestion points: Untrusted data enters the context through repository files read during the 'Discovery Workflow' (SKILL.md).
- Boundary markers: No specific delimiters or safety warnings are implemented to separate external file content from the agent's system instructions.
- Capability inventory: The agent possesses broad file-reading capabilities using tools like
rgand has the potential for file modification if the user explicitly initiates the 'cleanup' phase. - Sanitization: There is no mention of sanitizing or validating the content of the repository files before processing them.
Audit Metadata