scrape
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION] (LOW): The skill performs network operations using curl to
api.brightdata.com, which is a non-whitelisted domain. It transmits the user-provided URL and theBRIGHTDATA_API_KEYto this external service. - [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection because it ingests untrusted content from external websites. Ingestion points: Data enters the system via the
curlrequest to external URLs inscripts/scrape.sh. Boundary markers: Absent; the scraped markdown is returned without delimiters or instructions to the LLM to ignore embedded commands. Capability inventory: The skill usescurlfor API communication. Sanitization: No sanitization or filtering is performed on the scraped content before it is passed to the AI agent.
Audit Metadata