openspec-propose

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the openspec and codegraph CLI tools to perform codebase exploration and manage the lifecycle of change artifacts (proposals, designs, and tasks).
  • [PROMPT_INJECTION]: The skill processes external data that could contain malicious instructions, creating a surface for indirect prompt injection. \n
  • Ingestion points: Project source code symbols and verbatim code snippets retrieved via codegraph explore, CLI-provided instructions and metadata from openspec instructions, and the content of existing artifact files. \n
  • Boundary markers: The skill relies on structured templates for output but does not implement explicit delimiters or safety instructions to prevent the agent from following commands embedded within the project's source code or artifact dependencies. \n
  • Capability inventory: The agent has access to shell command execution (openspec, codegraph) and the ability to write files using the TodoWrite tool. \n
  • Sanitization: No specific sanitization, escaping, or filtering logic is described for the content extracted from the project codebase.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 05:53 PM
Security Audit — agent-trust-hub — openspec-propose