openspec-design

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from proposal.md to generate design documents, creating a surface for indirect prompt injection.
  • Ingestion points: The design and maintain commands read content from openspec/changes/{id}/proposal.md (SKILL.md).
  • Boundary markers: Absent. No delimiters or instructions to ignore embedded commands are used.
  • Capability inventory: The skill has file-read and file-write capabilities in the local directory.
  • Sanitization: Absent. No filtering or validation of external content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 06:17 AM
Security Audit — agent-trust-hub — openspec-design