verify-rfc

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted content from user-provided URLs or search results to generate verification checklists and search queries. Instructions embedded within these fetched documents could attempt to influence the agent's verification behavior.
  • Ingestion points: External document content is ingested in SKILL.md using the read_document tool.
  • Boundary markers: The skill does not implement boundary markers or instructions to isolate the fetched content as data.
  • Capability inventory: The agent has access to local file search tools and internal code search via code_search.
  • Sanitization: No sanitization or validation of the fetched document content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 06:51 PM
Security Audit — agent-trust-hub — verify-rfc