Skills
Navigate
skills/scavio-ai/skills/twitter-scraper-api/Gen Agent Trust Hub

twitter-scraper-api

Pass

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches and processes untrusted content from social media platforms (tweets, replies, and user profile metadata) which could contain instructions designed to influence the behavior of the agent.
  • Ingestion points: Data retrieved from the Scavio API endpoints defined in SKILL.md.
  • Boundary markers: Not specified; the instructions do not establish delimiters to isolate or identify external content.
  • Capability inventory: The skill facilitates network operations to the vendor's API but does not define local file system or system-level execution capabilities.
  • Sanitization: The skill directs the agent to return API data as-is without explicit validation or filtering of user-generated content.
  • [EXTERNAL_DOWNLOADS]: The skill suggests installing the langchain-scavio package (version 4.0.2), which is the official integration package for the vendor's service.
  • [COMMAND_EXECUTION]: The documentation provides implementation examples using the Python requests library to perform network calls to the api.scavio.dev service infrastructure.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 11, 2026, 10:44 PM