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
Risk Level
SAFE
Analyzed
Feb 26, 2026, 04:24 AM