hard-cut
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to analyze and refactor existing project source code, which serves as an ingestion point for untrusted data.
- Ingestion points: The agent is instructed to trace and process producers, consumers, fixtures, and tests within a codebase (SKILL.md).
- Boundary markers: No specific delimiters or instructions to ignore embedded prompts within the source code are provided.
- Capability inventory: The skill utilizes the agent's file modification and deletion capabilities to update codepaths and remove legacy logic (SKILL.md).
- Sanitization: There are no requirements for validating or sanitizing the content of the source code before it is processed by the agent.
Audit Metadata