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 | shthat 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
infshtool to perform various social media automation tasks. Access is restricted to theinfshcommand via theallowed-toolsfrontmatter 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
infshcommands, 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