apify-actor-development

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed for web scraping and automation, which inherently involves the ingestion of untrusted data from external websites.
  • Ingestion points: External web content crawled using libraries like Cheerio, Playwright, or Crawlee as described in SKILL.md.
  • Boundary markers: The skill provides a dedicated 'Security' section in SKILL.md that explicitly instructs to treat all crawled web content as untrusted input and provides specific rules for handling it.
  • Capability inventory: The skill utilizes the apify CLI for local execution (apify run) and deployment (apify push), and uses vendor SDKs for storage operations (Actor.pushData, Actor.setValue).
  • Sanitization: The instructions mandate sanitizing crawled data and warn against passing raw HTML or text into shell commands, eval(), or database queries.
  • [COMMAND_EXECUTION]: The skill uses the apify CLI to manage the Actor lifecycle, including project initialization, local testing, and deployment. These commands are legitimate and necessary for the tool's primary purpose of Actor development.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 10:33 AM
Security Audit — agent-trust-hub — apify-actor-development