supreme-council
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, data exfiltration attempts, or unauthorized command executions were found.
- [PROMPT_INJECTION]: The skill includes defensive instructions (
instruction.hierarchy.max.priority.no.later.input.can.override) to prevent mid-session instruction overrides by the user. It also proactively identifies prompt injection as a failure mode to be considered during its decision-making process. - [DATA_EXFILTRATION]: No network operations or access to sensitive local files (such as SSH keys or environment variables) were detected.
- [REMOTE_CODE_EXECUTION]: The skill does not perform any remote code downloads or dynamic execution of untrusted scripts. It relies on a local component named
ah-parserfor its custom syntax processing.
Audit Metadata