PPT Generator Pro
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlto discover API endpoints from the vendor's domains (fluxapay.xyz). This is a functional requirement for the integrated pay-per-use model and utilizes the author's own infrastructure. - [EXTERNAL_DOWNLOADS]: Fetches service discovery data and configurations from
proxy-monetize.fluxapay.xyzandmonetize.fluxapay.xyz. These downloads are from vendor-controlled resources and are documented neutrally as they are essential for the skill's operation. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it incorporates untrusted data into its generation pipeline.
- Ingestion points: User-provided document content collected in Phase 1.1 and style definitions read from the
styles/directory. - Boundary markers: There are no explicit delimiters or boundary markers used to separate user-provided content from the agent's internal instructions during prompt construction.
- Capability inventory: The skill has the capability to write files (images, videos, JSON, and HTML) to the local disk and perform network operations via external API calls.
- Sanitization: No sanitization or escaping of user input is specified before it is interpolated into generation prompts or the interactive HTML player (XSS risk).
Audit Metadata