group-search

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its document retrieval and synthesis workflow.
  • Ingestion points: Document content is ingested from the Yuque platform via the yuque_get_doc tool in SKILL.md.
  • Boundary markers: The prompt lacks clear delimiters or explicit instructions to the model to ignore instructions found within the retrieved text.
  • Capability inventory: The skill is limited to read operations (searching and fetching docs) and does not have access to sensitive file paths, persistent storage, or outbound network tools beyond the MCP environment.
  • Sanitization: No sanitization, filtering, or validation is performed on the content retrieved from documents before it is processed by the model for answer synthesis.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 09:12 AM
Security Audit — agent-trust-hub — group-search