calculate-ice-score
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill provides logical instructions for product management tasks. It guides the agent through an evaluation process based on explicitly provided evidence and predefined scoring tables.
- [NO_CODE]: No scripts, binaries, or executable code segments are present in the skill file. The process relies entirely on the language model's reasoning capabilities within its native environment.
- [PROMPT_INJECTION]: The instructions do not include any bypass attempts, role-play overrides (like DAN), or commands to ignore previous system instructions.
- [DATA_EXFILTRATION]: No network-enabled tools (like curl or wget) or sensitive file path access (like SSH keys or env files) are referenced. The instructions to write reports to a local directory are consistent with the skill's stated purpose.
Audit Metadata