scraping-twitter-list-members

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Twitter/X profiles, including user bios, names, and profile metadata. This creates an attack surface where malicious instructions embedded in public profiles could influence the agent's behavior during data processing.
  • Ingestion points: Twitter profile data fetched via the twitter-list-scraper actor (SKILL.md).
  • Boundary markers: The skill suggests outputting data in Markdown table or CSV/JSON formats, which provides structural boundaries but does not sanitize the content itself.
  • Capability inventory: The skill uses node and curl to interact with the Apify API and local file system for saving results.
  • Sanitization: No explicit sanitization or instruction-ignoring delimiters are mentioned for the fetched profile content.
  • [DYNAMIC_EXECUTION]: The skill exposes the customMapFunction parameter, which accepts a JavaScript function as a string to transform data objects. This allows for dynamic code execution within the Apify environment. While this is a native feature of the underlying actor for user customization, it represents a surface for code injection if the agent is manipulated into providing malicious logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 06:28 PM
Security Audit — agent-trust-hub — scraping-twitter-list-members