chaos-experiment
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill is designed to interact with the Harness Chaos Engineering platform via a dedicated MCP server.
- [COMMAND_EXECUTION]: The skill utilizes MCP tools (harness_create, harness_execute) to perform chaos engineering tasks. These operations are within the stated functional scope of the skill.
- [DATA_EXFILTRATION]: No evidence of data exfiltration or hardcoded credentials. The instructions use placeholders for all identifiers, and network activity is limited to the authorized MCP server interaction.
- [PROMPT_INJECTION]: The skill does not contain instructions that attempt to bypass safety filters or override agent behavior.
Audit Metadata