codebase-cleanup-tech-debt
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and process untrusted data from a codebase. However, this is inherent to its primary function as a code analysis tool.
- Ingestion points: The agent is instructed to scan and analyze local codebase files to identify technical debt (SKILL.md).
- Boundary markers: Absent. There are no explicit instructions or delimiters used to separate the codebase content from the agent's instructions.
- Capability inventory: The skill involves file-read operations and instructions for generating remediation plans which might involve file-write operations depending on the agent's toolset.
- Sanitization: None detected. The agent processes the code as-is to perform its analysis.
Audit Metadata