prd-planner
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes
Bash,Grep, andGlobtools to perform recursive filesystem searches on the local codebase (e.g.,grep -r ... src/) to identify patterns for edge case analysis. - [EXTERNAL_DOWNLOADS]: The skill uses a
WebSearchtool to retrieve research and best practice information from external internet sources during the PRD creation process. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection.
- Ingestion points: Untrusted data is brought into the context through
WebSearchresults and recursive codebase scans. - Boundary markers: The provided file templates do not implement delimiters or specific instructions to isolate ingested content from agent commands.
- Capability inventory: The skill has permission to use
Write,Edit,Bash, andWebSearchtools, allowing for filesystem modification and network interaction. - Sanitization: There is no evidence of validation or sanitization for the data retrieved from external web sources or local codebase files before it is processed.
Audit Metadata