regulatory-audit-generator

Pass

Audited by Gen Agent Trust Hub on Nov 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external user input to generate compliance reports.
  • Ingestion points: User-provided business descriptions, user groups, and data types collected in the compliance procedure outlined in "SKILL.md".
  • Boundary markers: None present; the instructions do not specify delimiters or warnings for the agent to ignore instructions embedded within user-supplied scenario descriptions.
  • Capability inventory: No execution capabilities, such as shell access, network operations, or file writing, are present in the skill's instructions or metadata.
  • Sanitization: No sanitization or validation of the user input is implemented.
  • [NO_CODE]: The skill consists entirely of markdown instructions and does not include any executable scripts, binary files, or package dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 22, 2026, 01:11 AM