prd-brainstorm
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes markdown content from the
docs/prd/chunks/directory, creating a surface where instructions embedded within those files could potentially influence the agent's output or actions.\n - Ingestion points: Content is ingested from the
docs/prd/chunks/directory during the '块澄清模式' (Chunk Clarify mode) as described inSKILL.md.\n - Boundary markers: The instructions do not define specific delimiters or boundary markers to differentiate between the data being processed and instructions that might be contained within that data.\n
- Capability inventory: The agent has access to
Read,Write,Glob,Grep, andAskUserQuestion. Its write capabilities are restricted to thedocs/prd/requirements/anddocs/prd/chunks/directories.\n - Sanitization: There are no sanitization or validation protocols mentioned to filter or escape content read from external files before it is processed by the agent.
Audit Metadata