adoption-summary

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external data which introduces a surface for indirect prompt injection.\n
  • Ingestion points: Section 4 of the Quick Start instructions requires gathering sources like petitions, court orders, and social-work reports.\n
  • Boundary markers: The instructions lack explicit markers or delimiters to separate ingested content from the agent's internal instructions.\n
  • Capability inventory: No executable scripts, network requests, or file system operations are present in the skill.\n
  • Sanitization: No sanitization or validation protocols are defined for the ingested data.\n- [NO_CODE]: The skill is composed entirely of markdown instructions and does not contain any Python, Node.js, or other executable code.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 07:55 PM