promo-workflow
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes command-line tools including
ffmpegandnpx hyperframesfor video rendering and processing. These tools are standard for the described purpose of generating MP4 files from HTML-based templates. - [EXTERNAL_DOWNLOADS]: The skill uses
npxto execute thehyperframesutility, which involves dynamically fetching the package from the npm registry if not already present. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted content from external product URLs and web search results.
- Ingestion points: Phase 1 (product URL scraping) and Phase 3 (web search results for assets) ingest external data into the agent's context.
- Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the workflow description.
- Capability inventory: The skill possesses the capability to write to the file system (within the
outputs/directory) and execute shell commands vianpxandffmpeg. - Sanitization: No explicit sanitization or validation of the scraped product information or web search results is documented.
Audit Metadata