iterative-retrieval
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill describes a best-practice pattern for context management and does not contain any malicious code, exfiltration logic, or unauthorized commands.- [SAFE]: The skill processes file content from the local codebase to evaluate relevance. While this constitutes an ingestion point for potentially untrusted data (Indirect Prompt Injection surface), it is the primary intended function of a retrieval skill and does not include exploitable capabilities or instructions that bypass safety filters.
Audit Metadata