recon
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external codebase content, creating a surface for indirect prompt injection if malicious instructions are present in source files.
- Ingestion points: Processes external codebase scopes and files in Phase 1 (Macro Anchor Grounding).
- Boundary markers: Absent; the instructions do not define delimiters or specific warnings to ignore instructions embedded in the analyzed code.
- Capability inventory: Uses file and symbol tools and can launch subagents for parallel processing.
- Sanitization: There is no mention of sanitization or filtering of content retrieved from the codebase.
Audit Metadata