twitter-automation

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download the belt CLI and additional skill modules from the inference-sh GitHub repository and official vendor domains.- [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to ingest external data from social media which may contain adversarial instructions.
  • Ingestion points: Data retrieved via x/user-get and x/post-get apps mentioned in SKILL.md.
  • Boundary markers: No explicit delimiters are specified to separate retrieved social media content from the agent's instructions.
  • Capability inventory: The agent can perform significant actions including posting tweets, sending direct messages, and following users via the belt command.
  • Sanitization: No specific sanitization or validation logic is defined for processing retrieved tweet or profile data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:20 PM
Security Audit — agent-trust-hub — twitter-automation