workflow-idea-to-spec

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a standard and well-structured workflow for transforming raw ideas into feature specifications. It utilizes internal research tools and human-in-the-loop review gates to ensure the quality and validity of the output.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection via user-provided ideas and external research data.
  • Ingestion points: Input from user vision prompts and results from the $web-research and $deep-research tools.
  • Boundary markers: None explicitly defined in the instruction text to separate untrusted research data from agent instructions.
  • Capability inventory: The skill allows writing documentation to the project repository and invoking sub-agents for task completion.
  • Sanitization: The workflow includes multiple explicit review gates ($why-review, $artifact-review) and user confirmation steps ($spec-clarify) to mitigate risks.
  • [COMMAND_EXECUTION]: The workflow orchestrates tasks using platform-native tool calls (prefixed with $) and authorizes sub-agents (spawn_agent) as needed for scaling. These operations are appropriate for the skill's purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 08:23 PM
Security Audit — agent-trust-hub — workflow-idea-to-spec