create-doc
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external YAML templates that serve as an ingestion point for instructions which the agent follows during document creation.
- Ingestion points:
SKILL.mdloads and parses YAML templates (Step 2) from theresources/directory or user-provided paths. - Boundary markers: There are no explicit boundary markers or instructions to ignore embedded prompts when processing the
instructionfields from the YAML templates. - Capability inventory: The agent has the capability to write to the file system (Step 4.f) and invoke external tools like
mermaid-architect(Step 4.h) andpm-checklist. - Sanitization: No sanitization or validation logic is present to filter malicious instructions within the template files.
- [PROMPT_INJECTION]: The 'YOLO Mode' feature allows users to bypass the mandatory step-by-step elicitation and verification process, increasing the risk of executing unintended or malicious instructions from a compromised template without human oversight.
Audit Metadata