ai-social-media-content
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs users to download and install the
infshCLI tool and refers to documentation hosted on GitHub atraw.githubusercontent.com/inference-sh/skills/.- [EXTERNAL_DOWNLOADS]: The skill suggests incorporating additional functionality by adding related skills from theinference-sh/skillsrepository using thenpx skills addcommand.- [COMMAND_EXECUTION]: Extensive use of Bash commands is provided for interacting with theinfshCLI, including account authentication (infsh login) and executing inference tasks for various AI models.- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection where user-supplied descriptions and scripts are processed by AI models. - Ingestion points: User-provided text prompts for image, video, and text generation tasks in
SKILL.md. - Boundary markers: Shell commands utilize structured JSON input objects (
--input '{...}') to encapsulate prompts. - Capability inventory: The skill uses the
Bash(infsh *)tool to perform remote AI inference and local file operations (e.g., writing results to.jsonfiles). - Sanitization: No client-side content sanitization is implemented; the skill relies on the safety filters of the underlying inference service provider.
Audit Metadata