Skills
skills/molechowski/agent-skills/edu-visual-trace/Gen Agent Trust Hub

edu-visual-trace

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to invoke the doc-mermaid-ascii command-line tool to generate structural diagrams, which is a core feature of the skill.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface by ingesting arbitrary user-provided concept descriptions. Ingestion points: User input for concept explanation (SKILL.md). Boundary markers: None specified. Capability inventory: Interaction with the doc-mermaid-ascii CLI tool. Sanitization: No input validation or escaping procedures are defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 09:35 PM