create-output-format

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external documentation to generate instructions for other agents, creating an indirect prompt injection surface.\n
  • Ingestion points: External URLs provided by users and processed by the WebFetch tool as described in SKILL.md.\n
  • Boundary markers: Absent. No instructions are provided to the agent to distinguish between documentation content and potential embedded malicious instructions.\n
  • Capability inventory: The skill writes markdown files (authoring.md, reading.md, updating.md, graph.md, about.md) to the local filesystem at skills/technical-planning/references/output-formats/{format-key}/. These files define logic for task creation, extraction, and graph building for downstream agents.\n
  • Sanitization: Absent. Content from external documentation is directly used to replace placeholders in scaffolding templates without validation or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 02:33 PM