marketing-video
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill operates as a marketing specialist, primarily reading local documentation and writing marketing assets to structured paths. No evidence of malicious intent or safety bypasses was found.
- [EXTERNAL_DOWNLOADS]: Fetches the 'agent-browser' skill from Vercel Labs' official GitHub repository for competitive research and SERP analysis tasks.
- [COMMAND_EXECUTION]: Provides standard setup instructions to install the 'agent-browser' CLI and Playwright dependencies via npm and npx for project environment preparation.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external web content using a browser tool for competitive research. While this creates a potential surface for instructions embedded in third-party websites to influence agent behavior, the risk is mitigated by the skill's narrow focus on marketing strategy generation and the absence of high-privilege capabilities such as arbitrary system command execution or sensitive credential access.
Audit Metadata