discovery-workshop

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through its document synthesis workflow.
  • Ingestion points: Untrusted workshop notes are ingested via user input and the Read tool as defined in SKILL.md.
  • Boundary markers: The prompt does not include delimiters or instructions to the model to ignore commands embedded in user-provided notes.
  • Capability inventory: The skill is granted Write, Edit, Grep, and Glob tools, which provide a path for potential unauthorized file system changes if a malicious prompt is processed.
  • Sanitization: No input validation or content filtering is implemented for the processed workshop notes.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 11:45 PM