social-media-publisher
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
child_process.spawnto executeyt_dlpviapython3for downloading media. This is implemented using an arguments array, which is a secure practice that prevents shell command injection. - [EXTERNAL_DOWNLOADS]: The skill facilitates the download of media from external URLs for social media posts. This is a primary function of the skill and is handled via established tools like
yt-dlpor the platform's hosted storage service. - [DATA_EXFILTRATION]: No unauthorized exfiltration was detected. All network operations are restricted to the PostPlus platform's infrastructure or authorized cloud storage providers for media uploads via a hosted bridge.
- [PROMPT_INJECTION]: While the skill processes user-supplied JSON requests and external media URLs, which represents an indirect prompt injection surface, this risk is mitigated by a mandatory 'Execution Approval' system. Sensitive operations require an explicit
--executeflag and a matching approval artifact (SHA256 digest), ensuring human oversight for all publishing actions.
Audit Metadata