Skills
skills/full-statck-skills/openspec-skills/openspec-apply/Gen Agent Trust Hub

openspec-apply

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill references documentation and workflow specifications from the OpenSpec project's public GitHub repository.
  • [PROMPT_INJECTION]: The skill processes instructions from local files like tasks.md and design.md to perform code generation and testing, representing an indirect prompt injection surface.
  • Ingestion points: The agent reads data from tasks.md, design.md, and the specs/ directory.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used for the ingested content.
  • Capability inventory: The skill is authorized to create/modify files and execute shell commands for testing.
  • Sanitization: No validation or content filtering is performed on the ingested task files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 04:14 AM
Security Audit — agent-trust-hub — openspec-apply