browserless
Pass
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlto interact with the Browserless API andjqto process the JSON output. - [DATA_EXFILTRATION]: The skill sends data payloads to
production-sfo.browserless.io. This is documented as the official endpoint for the Browserless service and is necessary for its functionality. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes content from arbitrary external websites. This is an inherent risk for any web-browsing tool.
- Ingestion points: Data is fetched from external URLs via the Browserless API as documented in
SKILL.md. - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are included in the prompt examples.
- Capability inventory: The skill uses
curlto perform network requests and writes temporary files to/tmp/. - Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the web before it is processed by the agent.
Audit Metadata