learn-anything-skill

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze a wide range of user-provided and external materials, including documents, repositories, and official documentation, creating an indirect prompt injection surface.\n
  • Ingestion points: Processes user-provided materials (screenshots, repositories, papers) and external research data fetched during the teaching flow as defined in SKILL.md.\n
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' directives to isolate external content from the agent's system instructions.\n
  • Capability inventory: The agent performs file writing operations to the local filesystem (specifically in the 'study/' directory) and interacts with the user based on processed data.\n
  • Sanitization: No explicit sanitization, filtering, or validation steps are mentioned for the external content before it is interpolated into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 03:16 AM
Security Audit — agent-trust-hub — learn-anything-skill