hermes-agent-mission-control
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs users to download and install the
minionsaipackage from the npm registry usingnpm install -gornpx. - [COMMAND_EXECUTION]: The instructions require executing the
minionscommand locally to start a web server on port 6969. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it allows an autonomous agent to process untrusted data.
- Ingestion points: Task descriptions provided via the web interface and files within the workspace directory analyzed by the agent.
- Boundary markers: None specified in the documentation to distinguish between instructions and data.
- Capability inventory: High; the Hermes Agent can autonomously execute tool calls, reasoning steps, and file system operations.
- Sanitization: No explicit sanitization or validation of the input data is mentioned before it is processed by the agent.
Audit Metadata