paw-mkt-product-context
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands for tool discovery and browser automation using the agent-browser utility.\n- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch the agent-browser tool from Vercel Labs' official GitHub repository and install associated dependencies like playwright.\n- [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves ingesting and analyzing untrusted data from external sources, which creates a potential surface for indirect prompt injection.\n
- Ingestion points: The agent is instructed to read content from live website URLs, social media platforms (LinkedIn, Twitter/X, Facebook Ads Library), and customer reviews.\n
- Boundary markers: The instructions do not specify using delimiters or "ignore instructions" markers for the ingested content.\n
- Capability inventory: The agent can write documents to the filesystem and execute shell commands for research purposes.\n
- Sanitization: No procedures for sanitizing or filtering external data before processing are documented.
Audit Metadata