bugs-are-annoying
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection through its ingestion of untrusted codebase files. * Ingestion points: All relevant project files are read in full during the audit process (Phase 2). * Boundary markers: The instructions do not define delimiters or specific markers to distinguish between code content and agent instructions. * Capability inventory: The skill is authorized to write to the local filesystem to create bug reports and apply code changes in 'Fix Mode'. It does not have network access. * Sanitization: No filtering or validation is specified for the content of the files being audited.
Audit Metadata