scraping-tweets-from-account

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external Twitter/X profiles via the Apify API.
  • Ingestion points: The skill fetches raw tweet text, replies, and media metadata from public Twitter accounts (documented in SKILL.md).
  • Boundary markers: The instructions lack explicit boundary markers or delimiters to prevent the agent from interpreting instructions embedded within scraped tweets.
  • Capability inventory: The skill utilizes node and curl for network requests and local file system operations (CSV/JSON output).
  • Sanitization: No sanitization or filtering logic is specified for the ingested tweet content before it is presented to the agent or saved to the local environment.
  • [COMMAND_EXECUTION]: The documentation includes instructions for the agent to execute a local helper script (node scripts/run_actor.js) and system-level curl commands to interact with the Apify REST API.
  • [EXTERNAL_DOWNLOADS]: The skill performs network requests to api.apify.com to trigger scraping actors and retrieve datasets. This is a well-known service and is consistent with the skill's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 06:37 PM
Security Audit — agent-trust-hub — scraping-tweets-from-account