dead-code-removal
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code files which may contain embedded instructions meant to subvert the agent's logic.
- Ingestion points: Source code files across various languages (Python, JavaScript, Java, etc.) are ingested for analysis in the 'Language Detection' and 'Detect Unused Elements' steps.
- Boundary markers: No explicit boundary markers or 'ignore' instructions are provided to the agent to protect against instructions hidden in comments or strings within the code being analyzed.
- Capability inventory: The skill includes instructions for 'Incremental Removal' and 'Backup Creation', granting the agent authority to modify the file system.
- Sanitization: No sanitization or safety-stripping is performed on the code content before it is processed by the agent's internal logic.
Audit Metadata