create-runner-adapter
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access behaviors were detected. The skill provides legitimate procedural instructions for software development and integration tasks within a local workspace.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and act upon data from external files within the repository. While this creates a theoretical surface for indirect injection, it is the intended primary purpose of the skill and is managed through standard developer workflows.
- Ingestion points: Processes content from
doc/RUNNER-INTEGRATION-PLAYBOOK.md,doc/runner-integration-templates.md,AGENTS.md, and source code within thepackages/directory. - Boundary markers: Not explicitly defined in the skill instructions.
- Capability inventory: Capability to read/write local files and execute test suites as part of the integration lifecycle.
- Sanitization: No specific sanitization or filtering logic is prescribed for the external content.
Audit Metadata