cross-platform-social-profile-search
Warn
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: MEDIUMPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains explicit instructions to override standard interaction protocols by directing the agent to perform actions without user oversight. Specifically, it states the agent should "install the missing dependency automatically without asking the user to confirm" and "do not request separate approval for dependency installation."
- [EXTERNAL_DOWNLOADS]: The instructions require the agent to download and install the BrowserAct CLI and associated skill from an external source (browseract.com/github.com) if they are not detected in the environment.
- [COMMAND_EXECUTION]: The skill assumes the ability to execute installation commands and run the BrowserAct CLI at runtime to fulfill data collection requests.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and process data from social media profiles (bios, names, handles, and activity), which are attacker-controllable sources.
- Ingestion points: Social media profile data, biographies, and engagement signals mentioned in
SKILL.md. - Boundary markers: There are no instructions defining delimiters or warnings for the agent to ignore potentially malicious instructions embedded in the scraped social media content.
- Capability inventory: The skill utilizes the
browser-acttool to perform web interactions and data extraction. - Sanitization: No sanitization, filtering, or validation steps are defined for the data collected from external platforms before it is processed or displayed.
Audit Metadata