skills/mdsmithaustin/pstack/teach/Gen Agent Trust Hub

teach

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a workflow for the agent to explain technical concepts. It does not contain code, remote dependencies, or suspicious instructions. It focuses on teaching techniques like using diagrams and avoiding jargon.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external code for analysis, which is a potential surface for indirect prompt injection. However, its capabilities are restricted to text and diagram generation. 1. Ingestion points: Source code files and technical documentation. 2. Boundary markers: None. 3. Capability inventory: Natural language output, Mermaid diagrams, and image generation tools. 4. Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 05:21 PM
Security Audit — agent-trust-hub — teach