ai-social-media-content
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the 'belt' CLI tool and references installation documentation hosted on the 'inference-sh' GitHub repository. These are legitimate resources required for the skill's primary function of content generation.
- [INDIRECT_PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection by interpolating user-provided text (such as concepts and topics) into shell command arguments.
- Ingestion points: Variables like '$CONCEPT' and '$topic' are used in bash command templates within
SKILL.md. - Boundary markers: Input strings are encapsulated within JSON payloads passed to the CLI tool.
- Capability inventory: The skill uses the
Bashtool (restricted to thebeltcommand) to interact with external AI models for text, image, and video generation. - Sanitization: No explicit sanitization of shell variables is shown in the provided examples, though the tool usage is limited to a specific binary.
Audit Metadata