content-repurposing
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
belt-sh/clidependency and references installation scripts from a remote GitHub repository (inference-sh/skills). - [COMMAND_EXECUTION]: Utilizes the
Bashtool to runbeltCLI commands for logging in and interacting with remote AI applications. - [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing untrusted external content (such as blog posts or transcripts) and passing it to AI models. This represents an indirect prompt injection surface, though no specific malicious exploitation is present in the static code.
Audit Metadata