Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill contains markdown documentation and metadata only. No executable scripts, binaries, or automated installation files were detected.\n- [PROMPT_INJECTION]: The skill relies on processing data from LinkedIn profiles and messages, creating a surface for indirect prompt injection.\n
- Ingestion points: Browser snapshots of LinkedIn messaging, notifications, and profile pages via the
browsertool.\n - Boundary markers: No explicit markers or instructions to ignore embedded commands are provided for processed external content.\n
- Capability inventory: The skill uses the
browsertool to navigate, click, and type within the user session.\n - Sanitization: No specific sanitization methods are listed; however, the skill mandates manual user confirmation for all outgoing messages and connection requests.
Audit Metadata