content-repurposing
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and suggests installation of the
beltCLI and additional skills from theinference-shGitHub repository and npm scope. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied content for repurposing, which creates an attack surface for indirect prompt injection.
- Ingestion points: Ingests blog posts and podcast transcripts in the content conversion recipes.
- Boundary markers: No explicit boundary markers are present in the examples to isolate input data.
- Capability inventory: The skill uses tools with network and publishing capabilities, such as
x/post-createandfalai/flux-dev-lora. - Sanitization: No sanitization of the processed content is specified in the transformation steps.
Audit Metadata