rfp-evaluate

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted RFP data (titles and descriptions) which are interpolated into AI prompts in the evaluateWithAI function. While this presents an indirect prompt injection surface, it is a standard design for AI evaluation tasks and has no access to dangerous system capabilities.
  • Ingestion points: RFP title and description passed to the AI provider.
  • Boundary markers: No specific delimiters are used to wrap external content.
  • Capability inventory: Restricted to logic evaluation and scoring via LLM.
  • Sanitization: No explicit text sanitization is performed on input text before prompt construction.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 03:08 PM