openspec-verify-change
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and interprets content from repository files (tasks, specs, and design documents) to generate verification reports. Malicious instructions placed in these files could potentially influence the agent's logic or output.
- Ingestion points: Artifact files (e.g.,
tasks.md,specs.md,design.md) identified throughopenspec instructions applyare read and parsed in steps 5, 6, and 7. - Boundary markers: The instructions lack explicit delimiters or safety prompts to ensure the agent ignores instructions embedded within the processed artifacts.
- Capability inventory: The agent is authorized to use the
openspecCLI and perform codebase searches based on the artifact content. - Sanitization: The skill does not implement validation or sanitization of the text extracted from markdown artifacts before the agent processes them.
Audit Metadata