idea-to-design-doc

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions do not contain any malicious patterns or attempts to bypass safety protocols. Natural instructional headers like 'Important constraints' are used for workflow guidance rather than adversarial overrides.\n- [COMMAND_EXECUTION]: The skill performs local file system operations to store and index project ideas. These actions are restricted to a user-defined local directory and are essential for the skill's note-taking functionality.\n- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests user-provided text into generated documents. However, this is inherent to its function as a drafting tool and is considered low risk in this context.\n
  • Ingestion points: User responses provided during the interactive interview process (SKILL.md).\n
  • Boundary markers: Absent; user input is directly incorporated into the output Markdown templates.\n
  • Capability inventory: Local file-write operations to the ./ideas/ folder.\n
  • Sanitization: No filtering or sanitization of user input is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 01:44 PM
Security Audit — agent-trust-hub — idea-to-design-doc