content-repurposing
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute the
infshCLI for tasks such as image generation (falai/flux-dev-lora), text-to-speech (falai/dia-tts), and social media posting (x/post-create). - [EXTERNAL_DOWNLOADS]: The documentation provides instructions to download and install related skills from the vendor's GitHub organization (
inference-sh/skills) usingnpx. - [PROMPT_INJECTION]: The skill's workflow involves processing untrusted external content (blogs and transcripts) to generate derivative assets for distribution. This configuration presents a surface for indirect prompt injection. Ingestion points: Processes blog content and podcast transcripts within conversion recipes. Boundary markers: No specific delimiters or instructions to ignore embedded commands are included in the recipes. Capability inventory: Includes capabilities to post to social media (
x/post-create) and generate various media assets. Sanitization: No explicit sanitization or input validation steps are documented for the source content.
Audit Metadata