web-scraper-api
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill makes network requests to
realtime.oxylabs.ioanddata.oxylabs.io. These operations are performed to access the official APIs provided by the skill's author for web scraping tasks. - [PROMPT_INJECTION]: Because the skill is designed to ingest data from external, untrusted websites, it creates a surface for indirect prompt injection attacks where malicious instructions hidden in scraped content could influence the agent's behavior.
- Ingestion points: Untrusted external data is returned to the agent within the
results[0].contentfield of the API response. - Boundary markers: The documentation does not specify the use of delimiters or specific instructions to the agent to treat the scraped content as data only and to ignore any embedded commands.
- Capability inventory: The skill allows the agent to fetch content from arbitrary URLs using Oxylabs' infrastructure.
- Sanitization: No sanitization, filtering, or validation of the retrieved content is described, meaning instructions embedded in scraped HTML could be passed directly to the model.
Audit Metadata