skills/schroneko/skills/x-post/Gen Agent Trust Hub

x-post

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install the xurl CLI tool from a third-party Homebrew repository (xdevplatform/tap/xurl).
  • [COMMAND_EXECUTION]: User-provided text is passed as arguments to shell commands via the xurl utility for tweeting and replying.
  • [PROMPT_INJECTION]: The skill processes untrusted user input that is subsequently posted to a public social media platform, creating an indirect prompt injection surface.
  • Ingestion points: User-provided text strings for posts, replies, and direct messages in SKILL.md.
  • Boundary markers: Technical delimiters are absent in command construction; however, the skill mandates a workflow requiring manual user approval before execution.
  • Capability inventory: Shell command execution via the xurl CLI tool across all functional instructions.
  • Sanitization: No explicit sanitization or escaping mechanisms are described for the input strings interpolated into commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 06:22 AM
Security Audit — agent-trust-hub — x-post