skills/openclaw/skills/tweet-cli/Gen Agent Trust Hub

tweet-cli

Warn

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the tweet-cli package directly from a third-party GitHub repository (github:0xmythril/tweet-cli#v1.0.0) which is not included in the trusted vendors list.
  • [CREDENTIALS_UNSAFE]: The tool requires and manages highly sensitive X (Twitter) API credentials, including Consumer Keys and Access Tokens, storing them in a local environment file at ~/.config/tweet-cli/.env.
  • [COMMAND_EXECUTION]: The skill executes shell commands using the tweet-cli binary, passing user-provided strings and URLs as arguments to the post, reply, and quote functions.
  • [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by processing untrusted data from URLs or user-supplied text.
  • Ingestion points: Arguments for tweet-cli reply and tweet-cli quote.
  • Boundary markers: None identified in the skill instructions.
  • Capability inventory: Execution of the tweet-cli command with shell access.
  • Sanitization: No input validation or sanitization is specified for the content being posted or the URLs being referenced.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 26, 2026, 04:15 PM