marketing-carousel-growth-engine
Warn
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill implements persistence by programmatically modifying the system cron schedule to automate its recurring execution and lifecycle. While this supports its autonomous 'Daily Carousel Pipeline' goal, modifying system-level scheduling is a significant persistence mechanism.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its core functionality involves scraping and processing untrusted content from arbitrary external websites via Playwright. This content influences content generation and subsequent publishing logic without explicit sanitization or the use of boundary markers. This risk is notably heightened by the skill's 'Zero Confirmation' policy, which instructs the agent to run the entire research-to-publish pipeline autonomously without user oversight.
- [EXTERNAL_DOWNLOADS]: The skill performs external downloads of browser binaries (Chromium) during the initialization of its Playwright-based web scraping components.
Audit Metadata