Data Spider
PassAudited by ClawScan on May 1, 2026.
Overview
Data Spider is a transparent instruction-only web-scraping integration that uses AIProx and a spend token, with no evidence of hidden code or mismatched behavior.
This skill appears coherent and purpose-aligned. Before installing, understand that it is not a local scraper: it sends URLs and extraction requests to AIProx and uses a spend token for paid API access. Protect the token and avoid using the skill on private, confidential, or access-controlled pages unless you are comfortable with the external data flow.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Anyone with access to the token may be able to use the paid service and potentially incur charges.
The skill requires reading a spend/authentication token to call the paid AIProx API. This is disclosed and purpose-aligned, but it is still credential-like authority.
| Env Read | AIPROX_SPEND_TOKEN | Authentication for paid API |
Use a limited or revocable spend token, keep it out of shared chats and files, monitor usage, and rotate it if exposed.
URLs, schemas, tasks, and webpage content may be visible to the external service providers involved in the extraction workflow.
The skill sends the user’s URL, extraction request, and resulting webpage analysis through external orchestration/model services. This is central to the stated purpose, but it crosses a data boundary.
AIProx routes to the data-spider agent ... Analysis is performed by Claude via LightningProx.
Use it only with webpages and extraction requests you are comfortable sending to AIProx and its model provider, and review the provider’s privacy and retention terms for sensitive use cases.