Bimiyun Search

AdvisoryAudited by Static analysis on May 6, 2026.

Overview

No suspicious patterns detected.

Findings (0)

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.

What this means

Search results could contain misleading or prompt-injection-style text from the web if the agent treats snippets as authoritative instructions.

Why it was flagged

The skill places external web result text into the output that an agent may read and reuse.

Skill content
"content": r.get("text") or r.get("snippet")
Recommendation

Treat search results as untrusted reference material, verify important claims, and do not follow instructions embedded in returned webpages unless the user explicitly asks.

What this means

Anyone with access to the configured API key may be able to use the user's Bimiyun account quota or permissions.

Why it was flagged

The script uses the Bimiyun API key as an authentication header for the search request, which is expected for this integration.

Skill content
"X-Api-Key": self.api_key
Recommendation

Use a dedicated Bimiyun key with appropriate limits, keep it out of shared logs and repositories, and rotate it if it may have been exposed.

What this means

Search queries, language settings, and the API key are sent to the configured search endpoint; a misconfigured endpoint could change where that data goes.

Why it was flagged

The skill sends search payloads to an external provider endpoint, and the endpoint can be overridden through environment or .env configuration.

Skill content
endpoint = os.environ.get("BIMIYUN_ENDPOINT") ... return "https://search.bimiyun.com/api/web"
Recommendation

Avoid putting highly sensitive private data in search queries and only set BIMIYUN_ENDPOINT to a trusted Bimiyun-compatible endpoint.