AGENT LAB: SKILLS

apify-competitor-intelligence

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
  • EXTERNAL_DOWNLOADS (MEDIUM): The skill requires the user to install '@apify/mcpc' globally via npm. Since 'apify' is not included in the trusted organizations list, this is an unverifiable external dependency.
  • CREDENTIALS_UNSAFE (MEDIUM): The skill uses a shell command 'grep APIFY_TOKEN .env' to programmatically extract an API token from a local environment file. Accessing .env files is generally high-risk, though here it is tied to the primary skill purpose.
  • COMMAND_EXECUTION (LOW): The workflow executes shell commands ('mcpc' and 'node') that interpolate user-defined actor IDs and JSON inputs, creating a surface for command injection if inputs are not properly validated.
  • INDIRECT_PROMPT_INJECTION (LOW): The skill is designed to ingest and summarize data from various third-party platforms like Facebook, Instagram, and YouTube. (1) Ingestion points: Scraped content and Actor READMEs; (2) Boundary markers: Absent; (3) Capability inventory: Shell and script execution; (4) Sanitization: Absent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 04:40 PM