guideline-generation

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Potential for Indirect Prompt Injection through processed source materials.
  • Ingestion points: The skill ingests data from external documents (PDF, DOCX, etc.) and meeting transcripts as described in SKILL.md.
  • Boundary markers: There are no specific boundary markers or 'ignore' instructions defined for the data ingestion phase to prevent the LLM from following instructions embedded within those documents.
  • Capability inventory: The skill has the capability to write and archive files in the .claude/ subdirectory of the user's working folder.
  • Sanitization: The workflow includes PII redaction and anonymization, but lacks sanitization against malicious prompt segments in the source material.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 05:28 PM