Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Zhihuiya Fulltext Image
v1.0.0通过专利ID或公开号获取专利文件中的全文附图(图纸、示意图、图表)。当用户询问专利图片、专利图纸、专利示意图、专利插图、全文附图、专利图表、专利技术图或想查看、下载专利文件中的嵌入图片、patent fulltext drawings, patent diagrams, technical drawings, p...
⭐ 0· 32·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
high confidencePurpose & Capability
The skill's stated purpose (retrieve patent fulltext images) matches the code and SKILL.md: it POSTs to https://tool-gateway.linkfox.com/zhihuiya/fulltextImage and returns image URLs. However the registry metadata says "Required env vars: none" while the code and API docs clearly require LINKFOXAGENT_API_KEY; this mismatch is an incoherence worth flagging.
Instruction Scope
SKILL.md and the Python script limit behavior to querying the Zhihuiya/LinkFox tool gateway and presenting image links, with provisions for pagination and error handling. One notable instruction set in the SKILL.md (and references/api.md) describes calling a separate Feedback API (https://skill-api.linkfox.com/api/v1/public/feedback) to report user feedback; that will transmit skillName, sentiment, category and content (potentially including user-provided text) to an external endpoint. This is within the skill's declared docs but could leak user input if confidential content is included.
Install Mechanism
There is no install spec; it's instruction-only plus a small Python script. Nothing is downloaded or written by an installer, which minimizes surface risk.
Credentials
The code and API reference require an API key via the LINKFOXAGENT_API_KEY environment variable (used as Authorization header), but the skill registry metadata lists no required env vars or primary credential—this inconsistency is problematic. Requiring a single service API key is proportionate for the stated purpose, but the manifest should declare it. Also note that feedback calls post user content to a separate endpoint (no auth shown), which may be unexpected and could expose sensitive input.
Persistence & Privilege
The skill is not always-enabled and doesn't request persistent privileges or modify other skills or system settings. It runs ad-hoc when invoked and does not require elevated or persistent presence.
What to consider before installing
This skill appears to implement exactly what it claims (fetch patent images from a LinkFox/Zhihuiya API), but there are a few issues to consider before installing:
- Manifest mismatch: the skill's code and API docs require LINKFOXAGENT_API_KEY, yet the registry metadata does not declare any required environment variables or a primary credential. Confirm with the publisher and avoid installing until the manifest correctly lists LINKFOXAGENT_API_KEY.
- External endpoints: the skill sends requests to https://tool-gateway.linkfox.com/zhihuiya/fulltextImage (authorized via your API key) and also documents a separate feedback endpoint (https://skill-api.linkfox.com) that will receive skillName and user-provided content. If you plan to query with confidential patent text or proprietary snippets, be aware those could be transmitted as feedback if the skill auto-reports; verify when and how feedback is sent, and whether it requires consent.
- API key handling: only provide LINKFOXAGENT_API_KEY if you trust LinkFox/this skill. Store the key securely (not in shared shells) and use a least-privilege key if possible. Rotate/revoke the key after testing.
- Ask the publisher to correct the skill manifest to declare required env vars and to clarify the feedback behavior and whether feedback posts are authenticated or public. If you cannot verify the endpoints or publisher trustworthiness, avoid installing or limit usage to non-sensitive queries.Like a lobster shell, security has layers — review code before you run it.
latestvk973ah9ncbw3nsatqtdd28x15184240f
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
