skills/dydoc/skills/research/Gen Agent Trust Hub

research

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from primary sources like official docs and source code, creating a surface for indirect prompt injection attacks.
  • Ingestion points: External sources, documentation, and code (SKILL.md).
  • Boundary markers: No delimiters or 'ignore' instructions are provided to isolate untrusted data.
  • Capability inventory: The skill allows writing findings to Markdown files in the repository (SKILL.md).
  • Sanitization: No mention of input filtering or validation for researched content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 06:28 AM
Security Audit — agent-trust-hub — research