codebase-cleanup

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and modify entire codebases, which are considered untrusted data sources.
  • Ingestion points: The agent reads source code, comments, and configuration files across multiple languages (JavaScript, TypeScript, Python, Rust, Go) during the research phase of each cleanup pass.
  • Boundary markers: The instructions lack explicit delimiters or "ignore instructions" directives when reading file content, which could allow malicious instructions embedded in comments or code to influence the agent's behavior.
  • Capability inventory: The skill utilizes file system tools (grep, git, bash) and possesses the capability to modify the codebase (edit) during its implementation phase.
  • Sanitization: There is no mention of sanitizing or validating the contents of the files before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 12:51 AM
Security Audit — agent-trust-hub — codebase-cleanup