aeon-skill-evals
Pass
Audited by Gen Agent Trust Hub on Jul 5, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill is configured for installation from the vendor's GitHub repository. This is a standard and expected deployment method for skills from this provider.\n- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it processes outputs from other agent skills (ingestion point: target skill outputs). Boundary markers are currently absent in the manifest configuration. However, the capability inventory is limited to passive assertion checking (regex, counts, and citations), and no sensitive operations are performed on the ingested data.\n- [SAFE]: Analysis of the skill instructions and configuration files revealed no presence of hardcoded credentials, persistence mechanisms, or obfuscated code. The local state file management follows standard practices.
Audit Metadata