eve-agent-optimisation
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze agent execution logs, which are external data sources that may contain untrusted input.
- Ingestion points: In SKILL.md, the 'Diagnostic Workflow' section instructs the agent to read execution records using
eve job diagnoseandeve job logs. - Boundary markers: No specific boundary markers or delimiters are defined to separate untrusted log content from the agent's internal instructions.
- Capability inventory: The agent is tasked with recommending changes to critical configurations including
SKILL.mdfiles, model selection, and permission policies likeyolomode. - Sanitization: The instructions do not include any steps for sanitizing or validating the content of the logs before they are processed by the agent.
Audit Metadata