skills/a5c-ai/babysitter/babysit/Gen Agent Trust Hub

babysit

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Installs the @a5c-ai/babysitter package from the official npm registry to provide orchestration capabilities.
  • [COMMAND_EXECUTION]: Executes shell commands to read configuration from versions.json and invoke the babysitter CLI for instruction retrieval.
  • [INDIRECT_PROMPT_INJECTION]: Dynamically fetches orchestration instructions from the output of the $CLI instructions:babysit-skill command, representing a standard but observable attack surface for tool-provided instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 02:27 PM
Security Audit — agent-trust-hub — babysit