resonance-ops-qa
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to run test suites (e.g.,
npm test,playwright). This is the intended primary functionality for a QA-focused agent and aligns with its stated purpose. - [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for untrusted data from feature specifications and pull requests, which could theoretically contain malicious instructions.
- Ingestion points:
SKILL.md(Feature specs, PR bodies, and verification requests). - Boundary markers: Not explicitly defined for external data within the prompt templates.
- Capability inventory: Execution of shell-based test runners and file system writes to
.resonance/learnings.jsonl. - Sanitization: No explicit sanitization or validation of the input data is mentioned before it is processed by the agent.
Audit Metadata