talking-head-production
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references external installation instructions and configuration files from a GitHub repository associated with the inference.sh service (
github.com/inference-sh/skills). - [COMMAND_EXECUTION]: The skill instructs the agent to execute commands using the
beltCLI tool to interface with AI models. The execution environment is restricted to thebeltcommand via theallowed-toolsYAML frontmatter configuration. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes external data.
- Ingestion points: User-provided image URLs, audio URLs, and text scripts defined in model input JSON (SKILL.md).
- Boundary markers: None present in the skill instructions.
- Capability inventory: Shell command execution via
belt app runusing the Bash tool. - Sanitization: No explicit sanitization or validation of external URLs or text scripts is described.
Audit Metadata