twitter-automation

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill provides an installation command curl -fsSL https://cli.inference.sh | sh that downloads and executes a shell script from the vendor's primary domain to install the necessary infsh CLI tool.
  • [COMMAND_EXECUTION]: The skill executes the infsh tool to perform various social media automation tasks. Access is restricted to the infsh command via the allowed-tools frontmatter configuration.
  • [DATA_EXFILTRATION]: The skill facilitates sending user-provided content to Twitter/X. This is the intended core functionality and uses the vendor's official infrastructure for API interaction.
  • [PROMPT_INJECTION]: The skill processes untrusted user input via JSON payloads in infsh commands, creating a potential surface for indirect prompt injection. Ingestion points: command arguments in SKILL.md examples. Boundary markers: JSON structure. Capability inventory: execution of infsh apps. Sanitization: none explicitly defined in instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 09:10 PM
Security Audit — agent-trust-hub — twitter-automation