paw-mkt-email
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install the
agent-browsertool from Vercel Labs' official GitHub repository to support research tasks. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a significant attack surface for indirect prompt injection as it is designed to audit live website URLs and perform automated research on social platforms and competitor dashboards.
- Ingestion points: The skill ingests untrusted data from live website URLs provided by the user and through browser-based research on external platforms (LinkedIn, Twitter, Facebook Ads Library).
- Boundary markers: The instructions do not define specific delimiters or warnings to ignore embedded instructions within the crawled content.
- Capability inventory: The agent has the capability to execute browser commands, fetch remote content, and write marketing deliverables to the local file system.
- Sanitization: There are no explicit sanitization or filtering steps mentioned for the content retrieved from external URLs before it is processed by the agent.
Audit Metadata