request-character
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local command using 'npm run neta' to fetch character data, which is its primary and intended function.
- [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface (Category 8).
- Ingestion points: The '--name' parameter processes character names which can be provided by external data or other agents.
- Boundary markers: There are no explicit delimiters or instructions to the model to ignore potential commands embedded within the name strings.
- Capability inventory: The skill allows execution of shell commands through the npm environment.
- Sanitization: No input validation or filtering is described in the skill documentation for the name parameter.
Audit Metadata