13-action-plan
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data retrieved from an external source (a client's Notion page) to generate a strategic action plan.
- Ingestion points: The skill reads Stage, SMF gap, ICP, and various artifacts (03-12) from the client's Notion page as defined in the
argument-hintand instructions. - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to treat the Notion content strictly as data or to ignore any embedded instructions.
- Capability inventory: The skill has permission to write to the client's Notion workspace, specifically creating a sub-page named '13 · Action Plan 30-90-180'.
- Sanitization: There are no explicit instructions for sanitizing, escaping, or validating the content retrieved from Notion before it is processed or written back to the workspace.
Audit Metadata