eve-agent-optimisation

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized network operations were detected in the skill content.
  • [COMMAND_EXECUTION]: The skill uses the vendor-specific 'eve' CLI toolset (eve job diagnose, eve job logs, eve job receipt) to access diagnostic metadata. These commands are used for their intended purpose of performance analysis.
  • [PROMPT_INJECTION]: The skill processes agent execution logs, which constitutes an indirect prompt injection surface. Ingestion points: eve job logs <job-id> (SKILL.md). Boundary markers: Absent. Capability inventory: eve CLI tool suite. Sanitization: Absent. The risk is mitigated by a hard rule prohibiting the agent from modifying harness, model, or permission policies without prior user approval, maintaining a safe human-in-the-loop workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 02:40 PM