playwright-explore-website
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from external, untrusted websites to identify functionalities and user flows. This creates a surface for indirect prompt injection, where malicious instructions hidden on a webpage could attempt to influence the agent's actions.
- Ingestion points: The skill uses
browser_navigateandbrowser_snapshot(SKILL.md) to load and analyze external web content. - Boundary markers: No specific delimiters or warnings for the agent to ignore instructions embedded in the webpage content are defined in the skill instructions.
- Capability inventory: The skill utilizes browser interaction tools (
browser_navigate,browser_snapshot,browser_close). It does not appear to have file-write or arbitrary command execution capabilities. - Sanitization: There is no evidence of sanitization or filtering applied to the content retrieved from the web before the agent processes it.
Audit Metadata