pm-user-story
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell script named
check-update.shduring the preamble phase to verify versioning and updates. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted data from requirement documents to generate project tasks.
- Ingestion points: The skill reads input from
docs/02-方案设计/PRD产品需求文档.mdanddocs/02-方案设计/功能细节拆解.md. - Boundary markers: No explicit delimiters or "ignore instructions" warnings are utilized when interpolating document content into agent prompts.
- Capability inventory: The skill possesses the capability to execute shell commands (
Bash), write files to the local environment (Write), and delegate tasks to sub-agents (Agent). - Sanitization: No sanitization, validation, or filtering is performed on the ingested PRD content before processing.
Audit Metadata