ads-publish
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local script
scripts/zernio_publish.pyusing the Bash tool to handle the logic of communicating with the Zernio API. - [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted content from the
campaign-brief.mdfile to extract social media captions. - Ingestion points: Reads
campaign-brief.mdto extract text from platform-specific markdown sections. - Boundary markers: Uses specific markdown headers (e.g.,
## Instagram caption) as delimiters to identify relevant content. - Capability inventory: The skill uses Bash for script execution, Read/Write for asset management and reporting, and AskUserQuestion for confirmations.
- Sanitization: No specific sanitization or filtering of the extracted text is described; however, the skill mandates a quality gate where the user must explicitly confirm the plan before publication.
Audit Metadata