pdca

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute curl for checking local server responses and npx playwright test for running end-to-end tests. These commands are part of the intended verification workflow.
  • [EXTERNAL_DOWNLOADS]: It recommends installing the @playwright/test package, which is a trusted and standard tool for web application testing.
  • [PROMPT_INJECTION]: The skill processes multiple project documents to maintain consistency across the workflow, which presents an indirect prompt injection surface.
  • Ingestion points: The skill reads files from the docs/ directory tree, such as docs/00-pm/*.prd.md and docs/01-plan/*.plan.md.
  • Boundary markers: No explicit delimiters or instructions to disregard embedded content are used during document ingestion.
  • Capability inventory: The skill has access to Bash, Write, Edit, and Task tools, which are powerful capabilities.
  • Sanitization: There is no evidence of validation or sanitization of the content read from markdown files before it is used as context for subsequent agent phases.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 02:23 AM
Security Audit — agent-trust-hub — pdca