ai-on-saas-discovery-and-qualification

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill requires the agent to analyze untrusted external data such as tender documents and architecture records to generate proposal content, creating a surface for indirect prompt injection.
  • Ingestion points: Tender documents, discovery evidence, and architecture records processed during the qualification workflow.
  • Boundary markers: The instructions lack explicit delimiters or directions to ignore embedded commands within ingested data.
  • Capability inventory: The skill is authorized to read workspace files and write to BRIEF.md and other proposal artifacts.
  • Sanitization: No instructions for sanitizing or validating input data are present.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 06:11 AM
Security Audit — agent-trust-hub — ai-on-saas-discovery-and-qualification