twitter-automation

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash(infsh *) tool, which is restricted in the frontmatter to only allow commands starting with the vendor's specific CLI (infsh). This configuration effectively limits the execution scope to the intended functionality.
  • [EXTERNAL_DOWNLOADS]: The skill references the vendor's official website (inference.sh), documentation, and a CLI installation guide hosted on their GitHub repository. These resources are consistent with the vendor's identity and stated purpose.
  • [DATA_EXFILTRATION]: No patterns of unauthorized data collection or exfiltration were identified. Network operations are directed through the vendor's CLI for the purpose of interacting with the X (Twitter) API as described.
  • [SAFE]: The skill contains no signs of prompt injection, obfuscation, or persistence mechanisms. Its behavior is transparent and aligns with its description as a social media automation tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 01:58 PM
Security Audit — agent-trust-hub — twitter-automation