brainstorming
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting data from external project files and documentation, creating a surface for indirect prompt injection attacks.
- Ingestion points: Step 1 (Understand the Current Context) directs the agent to review project files, documentation, plans, and prior decisions from the local environment.
- Boundary markers: The instructions do not implement delimiters or safety warnings to ignore instructions that may be embedded within the project files being reviewed.
- Capability inventory: The skill involves reading project files (Step 1) and writing the final design and decision logs to the filesystem (Documentation section).
- Sanitization: The skill lacks logic to sanitize, filter, or validate the content of the external files it processes.
Audit Metadata