opsx-apply

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the openspec and codegraph CLI tools to retrieve task status, fetch implementation instructions, and synchronize the codebase.
  • [PROMPT_INJECTION]: The skill is designed to process output from external CLI tools to guide its actions, which constitutes a standard indirect prompt injection surface for automation tools.
  • Ingestion points: Output from openspec status, openspec instructions apply, and codegraph explore.
  • Boundary markers: The skill does not define explicit delimiters for content ingested from these tools.
  • Capability inventory: Includes the execution of project-specific CLI tools and management of task completion states.
  • Sanitization: The skill relies on the output of trusted development tools without implementing additional internal filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 05:53 PM
Security Audit — agent-trust-hub — opsx-apply