animate-objects

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to establish ongoing automation and persistent execution cycles using tools such as cron, git hooks, and file watchers like watchexec.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and act upon data from potentially untrusted external sources. * Ingestion points: Pulls data from sources including CSV, YAML, JSON, API polls, and webhooks to trigger automated reactions. * Boundary markers: Procedure requires defining 'no-touch boundaries' and success conditions, though it lacks technical sanitization requirements. * Capability inventory: Employs cron, watchexec, GitHub Actions, and script generation to perform autonomous tasks. * Sanitization: Relies on manual confirmation gates ('Stop for explicit confirmation') before the agent performs live actions.
  • [COMMAND_EXECUTION]: The skill generates and runs scripts to implement autonomous logic and update static artifacts based on external triggers.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 09:14 AM
Security Audit — agent-trust-hub — animate-objects