unslop
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code diffs and applies modifications based on those inputs, creating a vulnerability surface for indirect prompt injection.
- Ingestion points: The skill operates on code diffs and surrounding source code provided in the agent's context (referenced in SKILL.md).
- Boundary markers: The instructions lack explicit directives for the agent to ignore or isolate natural language instructions that might be embedded within the code comments or strings being processed.
- Capability inventory: The skill instructs the agent to perform code deletions, inlining, and type modifications across the codebase, and suggests running verification tests (SKILL.md).
- Sanitization: There is no evidence of input validation or sanitization to prevent the agent from interpreting comments in the diff as new instructions.
Audit Metadata