twitter-post
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill interacts with the
twCLI tool. It implements a strong security posture against command injection by mandating that user-supplied input (tweet directions) be written to a temporary local file rather than being passed through shell interpolation or PTY sequences. - [EXTERNAL_DOWNLOADS]: The manifest identifies an update manifest hosted on GitHub (
ohmyskyhigh/threadwave-skill) and a setup URL onthreadwave.xyz. These are standard vendor resources for the skill's functionality and do not represent a security risk. - [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted user content to generate or publish tweets. It mitigates risk through the use of localized templates and a strict dry-run/approval workflow that requires explicit user confirmation before any action is dispatched.
- [DATA_EXFILTRATION]: The instructions explicitly forbid exposing user content, raw payloads, private references, or local paths in diagnostic issue reports, which protects against accidental data leakage during troubleshooting.
Audit Metadata