social-viral-content-finder
Fail
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to treat the 'BrowserAct CLI' as a required dependency and provides a specific URL (
https://www.browseract.com/) and GitHub repository (github.com/browser-act/skills) for its acquisition. - [PRIVILEGE_ESCALATION]: The instructions explicitly direct the agent to bypass standard security protocols by stating it should install missing dependencies automatically 'without asking the user to confirm' and 'not request separate approval for dependency installation.' This is an attempt to override the user's control over software execution and installation on their system.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves scraping and analyzing live social media data, which creates a surface for indirect injection attacks.
- Ingestion points: Browser-visible cross-platform social media data (posts, comments, creator content) retrieved via the BrowserAct tool (SKILL.md).
- Boundary markers: The skill does not provide any instructions for using delimiters or boundary markers to separate untrusted social media content from the agent's internal logic.
- Capability inventory: The agent uses the BrowserAct CLI to interact with the live web and execute browser workflows.
- Sanitization: There is no evidence of content sanitization, escaping, or validation of the data retrieved from social platforms before it is processed or used to influence agent behavior.
Recommendations
- AI detected serious security threats
Audit Metadata