runhuman-testing

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the execution of runhuman CLI commands (e.g., create, status, results) to manage QA testing workflows and project configurations.\n- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the runhuman global package from the npm registry, which is a resource provided by the vendor, volter-ai.\n- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface (Category 8) as it processes data from external sources.\n
  • Ingestion points: External feedback from human testers is retrieved through the runhuman results command in SKILL.md.\n
  • Boundary markers: There are no delimited blocks or instructions provided to the agent to treat the retrieved feedback as untrusted content.\n
  • Capability inventory: The agent can execute CLI commands, manage API keys, and interact with GitHub integrations through the runhuman tool.\n
  • Sanitization: No sanitization or validation logic is specified for the feedback content before it enters the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 11:34 PM