one-initiative-brief
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided information and task data from the workspace to generate documentation, which represents an attack surface for indirect prompt injection.\n
- Ingestion points: User responses during Phase 1 (Context) and task search results retrieved via search-tasks in Phase 2 (Related work).\n
- Boundary markers: Instructions focus on maintaining markdown formatting and media integrity but do not include explicit delimiters to isolate ingested data from the instruction stream.\n
- Capability inventory: The skill has the capability to create and modify records using the create-initiative, update-initiative, and patch-document tools.\n
- Sanitization: The instructions do not specify any sanitization, filtering, or validation steps for content retrieved from external task searches before it is incorporated into the brief.
Audit Metadata