openspec-verify-change
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by ingesting and processing untrusted project files to drive its verification logic.
- Ingestion points: The skill reads
tasks.md,design.md, and multiple markdown specification files from theopenspec/changes/directory. - Boundary markers: Absent. The instructions do not utilize XML tags, triple quotes, or specific guidance to the agent to disregard instructions found within the analyzed artifacts.
- Capability inventory: The skill executes
openspecCLI commands and performs recursive codebase searches for implementation evidence. - Sanitization: Content from external files is parsed directly for requirements (e.g., searching for "### Requirement:") and status checkboxes without escaping or validation.
Audit Metadata