paw-mkt-product-context
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install the
agent-browsertool from Vercel Labs' official GitHub repository and the npm registry to support automated research tasks. - [COMMAND_EXECUTION]: The skill utilizes shell commands for environment discovery (
tool-discovery.sh), browser profile management (chrome-profiles.sh), and executing browser automation via theagent-browserCLI. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from live website URLs and external strategy documents (SOSTAC files) to generate marketing positioning.
- Ingestion points: Data retrieved via
agent-browser,WebFetch, and local markdown files in the project workspace. - Boundary markers: The instructions lack explicit delimiters or specific guardrail prompts to isolate untrusted external content from the agent's core instructions.
- Capability inventory: The skill possesses the ability to write files to the local
.pawbytesdirectory and execute local scripts and CLI tools. - Sanitization: There is no evidence of specific validation, filtering, or escaping logic for the marketing intelligence gathered from external sources.
Audit Metadata