finding-trending-twitter-topics-for-content

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions to execute local scripts (node scripts/run_actor.js) to interact with the Apify platform. This is a standard integration method for Apify-based skills.
  • [EXTERNAL_DOWNLOADS]: The skill references and makes REST API calls to api.apify.com. These are legitimate interactions with a well-known service for the purpose of scraping public social media data.
  • [CREDENTIALS_SAFE]: The skill correctly instructs users to manage their APIFY_TOKEN via environment variables or .env files, which is an industry-standard security practice.
  • [INDIRECT_PROMPT_INJECTION]: While the skill processes external tweet data, it includes structured output formats and scoring logic that mitigate the risk of data being interpreted as instructions. The risk surface is present but managed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 06:42 PM
Security Audit — agent-trust-hub — finding-trending-twitter-topics-for-content