T09 · Insecure Skill Coding Practices
- Location
SKILL.md:41- Finding
Hard-Coded API Credential and Unsafe OAuth Token Transmission
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This Baidu image-recognition skill is coherent, but it needs Review because it can fetch arbitrary URLs and send image data to Baidu while handling API credentials unsafely.
Install only if you are comfortable sending images to Baidu Cloud and can revise the examples before use. Credentials should be moved to protected configuration, tokens should not be placed in URLs where avoidable, and remote URL inputs should be restricted to validated public HTTPS image URLs with timeouts, size limits, and content checks.
SKILL.md:41Hard-Coded API Credential and Unsafe OAuth Token Transmission
SKILL.md:55Unrestricted User-Controlled URL Fetch Enables Server-Side Request Forgery
At L005 the document states the skill is complete and callable, but the primary code example still uses SECRET_KEY = "需要补充" at L042, which means authentication cannot work as written. Later examples also rely on get_access_token() and encode_image() at L099-L102 and L144-L145 without defining them anywhere in the file, reinforcing that the implementation is not actually ready as claimed.
The skill accepts local images or image URLs and transmits the image contents to Baidu Cloud for processing, but the documentation does not clearly disclose this data transfer to users. This is dangerous because users may unknowingly submit sensitive personal, commercial, or internal images to a third-party service, creating privacy, compliance, and data-handling risks.
整份技能文档及面向用户的话术均默认且仅使用中文,例如“现在你可以”“直接吩咐”等,没有说明该技能仅面向中文用户,也未提供语言选择。根据该规则,未经过用户选择而强制单一语言/locale 可能构成自然语言政策问题。