skills/mattpocock/skills/research/Gen Agent Trust Hub

research

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill is designed for research and documentation purposes, with no executable code or malicious patterns detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an inherent attack surface for indirect prompt injection as it is designed to ingest and process untrusted external data.
  • Ingestion points: Official documentation, source code, and APIs (referenced in SKILL.md).
  • Boundary markers: No delimiters or ignore instructions are specified for external content.
  • Capability inventory: The agent has the capability to write research findings into Markdown files in the local repository (SKILL.md).
  • Sanitization: No explicit sanitization of the external content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 01:07 PM
Security Audit — agent-trust-hub — research