iterative-retrieval
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill implements an iterative loop that ingests content from external codebase files to refine context retrieval, creating a surface for indirect prompt injection.
- Ingestion points: Codebase files retrieved via the
retrieveFilesconceptual function inSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing retrieved file content.
- Capability inventory: The agent performs content evaluation, relevance scoring, and gap identification across all retrieved files.
- Sanitization: There is no evidence of sanitization, validation, or filtering of the content retrieved from the codebase before it is used to influence subsequent retrieval queries.
Audit Metadata