score-agent-response-quality
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists solely of markdown instructions and a response template. It does not perform any shell commands, network requests, or file system modifications.
- [NO_CODE]: There are no associated scripts or programming logic (e.g., Python or Node.js) included with the skill, which significantly reduces the attack surface.
- [DATA_EXFILTRATION]: While the skill analyzes user-provided text, it does not include instructions to send that data to external servers. It also proactively instructs the agent to suggest redacting Personally Identifiable Information (PII) before processing input.
- [PROMPT_INJECTION]: The instructions are clear and do not contain patterns intended to bypass the agent's safety protocols or extract system prompts. The interpolation of user data is used for evaluation purposes within the established rubric.
Audit Metadata