pm-prd-review

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a preamble that executes a local shell script (check-update.sh) via the Bash tool. This script is used for update checks and directory setup, representing the execution of code external to the SKILL.md file itself.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external documents (PRD, BRD, MRD) that may contain untrusted content. A vulnerability exists where malicious instructions embedded in these documents could influence the agent, potentially leveraging its Bash and Write permissions to perform unintended actions.
  • Ingestion points: Documents located in docs/02-方案设计/ or other user-specified paths.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined for the Read operations.
  • Capability inventory: Access to Bash (shell commands), Write (file creation/modification), and Read (file system access).
  • Sanitization: The instructions do not specify any validation or sanitization of the content extracted from the documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 06:20 AM
Security Audit — agent-trust-hub — pm-prd-review