investigation-add

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data to surface significant items, creating a surface for indirect prompt injection.
  • Ingestion points: The skill ingests data from user-provided notes and email exports as specified in SKILL.md.
  • Boundary markers: There are no delimited boundaries or specific instructions to ignore embedded commands within the ingested data.
  • Capability inventory: The skill loads and executes a separate reference skill 'internal-investigation' to process the content.
  • Sanitization: No sanitization, validation, or escaping of the external content is documented before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 03:58 PM
Security Audit — agent-trust-hub — investigation-add