governance-and-board-charter
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted client data, including constitutions, bylaws, and registry records, creating a surface for indirect prompt injection attacks.
- Ingestion points: Intake of client governing instruments and interview data as specified in the Required Inputs and Capability Contract sections of
SKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within the ingested client documents.
- Capability inventory: The skill is restricted to generating text-based deliverables (governance frameworks, charters, matrices). It lacks dangerous capabilities such as network exfiltration, arbitrary command execution, or sensitive file system access.
- Sanitization: No specific filtering or sanitization steps are defined for external data processing.
Audit Metadata