pdca

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface through its automated analysis and iteration workflows.\n
  • Ingestion points: The 'Analyze' (Check) phase reads implementation code from the src/ directory and design documents from docs/ to compare them.\n
  • Boundary markers: There are no explicit delimiters or instructions to treat ingested code as untrusted data or to ignore embedded instructions within that code.\n
  • Capability inventory: Across its phases, the skill calls MCP tools (bkit_pdca_analyze, bkit_pdca_plan) and possesses the capability to write to docs/ and modify code files in src/ (during the 'Iterate' phase).\n
  • Sanitization: The skill does not perform sanitization, escaping, or validation of the source code content it ingests before using it to generate analysis reports or code modifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 07:25 PM