iterative-retrieval
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill implements a workflow for reading and scoring the relevance of codebase files (e.g., src/**/*.ts), which creates a surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: Codebase files identified via glob patterns defined in SKILL.md.
- Boundary markers: Absent; the skill does not specify delimiters or instructions to ignore embedded prompts in retrieved content.
- Capability inventory: File retrieval and relevance scoring logic as described in SKILL.md.
- Sanitization: Absent; the pattern does not include validation or filtering of retrieved content before processing.
Audit Metadata