brainstorm
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to read external repository data, creating a potential attack surface for indirect prompt injection.\n
- Ingestion points: The agent is instructed to read existing brainstorming logs in
docs/brainstorm/, Architecture Decision Records (ADRs), and general repository documentation to establish context for the session.\n - Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the ingested repository content.\n
- Capability inventory: The skill possesses file system capabilities, specifically the creation of directories and the writing of markdown files to the
docs/brainstorm/path.\n - Sanitization: No validation or sanitization procedures are specified for the content extracted from repository files before it is processed by the agent.
Audit Metadata