twitter-alpha

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze approximately 350 external posts from Twitter/X and LinkedIn, creating an attack surface for indirect prompt injection.
  • Ingestion points: Data is pulled from external sources using POST /v1/scrape/twitter/search, /v1/scrape/twitter/user, and POST /v1/scrape/linkedin/posts as described in SKILL.md.
  • Boundary markers: The skill lacks explicit boundary markers or instructions for the agent to ignore or delimit instructions that might be embedded within the scraped social media content.
  • Capability inventory: The agent performs network read operations via API calls and generates formatted markdown output based on the external data.
  • Sanitization: There is no mention of sanitization, filtering, or validation of the content retrieved from external platforms before the agent processes and ranks it for 'alpha'.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 02:23 AM
Security Audit — agent-trust-hub — twitter-alpha