Back to skill
Skillv0.1.0

ClawScan security

Straker Verify · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignFeb 11, 2026, 9:33 AM
Verdict
benign
Confidence
high
Model
gpt-5-mini
Summary
The skill is an instruction-only wrapper for the Straker Verify API that only requires a single API key and its requests, scope, and requirements are consistent with the stated translation/verification purpose.
Guidance
This skill appears to legitimately wrap the Straker Verify API. Before installing: (1) confirm you obtained STRAKER_VERIFY_API_KEY from the official Straker.ai account or admin; (2) review Straker.ai's privacy/security policy if you will upload sensitive content — translations are sent to an external service; (3) avoid uploading highly sensitive data unless permitted by your policies; (4) verify the repository/homepage links and rotate the API key if you suspect it was shared; and (5) if you need offline/local translation, do not use this skill.

Review Dimensions

Purpose & Capability
okName/description map directly to using the Straker Verify translation API; the only required credential is STRAKER_VERIFY_API_KEY which is appropriate for an API-backed translation service.
Instruction Scope
okSKILL.md contains plain CURL examples and prompts for creating projects, uploading files, checking status, and downloading results. The instructions only reference files the user would intentionally upload and the declared API endpoints; there is no instruction to read unrelated system files or other environment variables.
Install Mechanism
okNo install spec and no code files — this is instruction-only, so nothing is written to disk by the skill itself. Low install risk.
Credentials
okOnly a single API key (STRAKER_VERIFY_API_KEY) is requested and it is the primary credential needed to authenticate to the documented endpoints; no unrelated secrets or system paths are requested.
Persistence & Privilege
okalways is false and the skill does not request persistent system-wide privileges; autonomous invocation is allowed by platform default but not excessive here.