apify-actor-development

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install development tools and dependencies from well-known registries (NPM and PyPI). All external documentation and reference links point to official domains belonging to well-known technology services.
  • [INDIRECT_PROMPT_INJECTION]: The skill establishes a framework for processing external web data, which is an inherent ingestion surface for indirect prompt injection.
  • Ingestion points: Untrusted web content retrieved by actors (referenced in SKILL.md).
  • Boundary markers: The skill instructions demand strict input/output validation and the use of defined schemas.
  • Capability inventory: Actors possess network and storage capabilities, but the skill advises against combining these with raw data handling.
  • Sanitization: Mandatory rules are provided to sanitize crawled content and avoid its use in executable contexts.
  • [COMMAND_EXECUTION]: The skill uses standard CLI tools for development workflows. It explicitly warns against insecure practices such as piping remote URLs into a shell and provides instructions for preventing credential leakage in command history.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 01:25 PM
Security Audit — agent-trust-hub — apify-actor-development