openspec-ff

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists exclusively of instructional Markdown content. It does not include any Python or Node.js scripts, executables, or automated command execution logic.
  • [PROMPT_INJECTION]: The skill defines a workflow for generating documents based on previous artifacts (e.g., generating specifications from a proposal). This creates a surface for indirect prompt injection, as the agent reads existing local files to generate new ones.
  • Ingestion points: Reads proposal.md, specs/**/*.md, and design.md from the openspec/changes/ directory.
  • Boundary markers: None specified in the instructions.
  • Capability inventory: The skill is designed for reading and writing markdown files in a specific local project directory.
  • Sanitization: None specified.
  • [EXTERNAL_DOWNLOADS]: The skill includes a reference link to documentation on GitHub (github.com/Fission-AI/OpenSpec). This is a standard documentation reference and does not involve the download or execution of remote code.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 12:35 PM