v1.0.0

Baidu Content Censor

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 8:05 AM.

Analysis

The skill matches its stated purpose of Baidu text/image moderation, but it sends submitted content to Baidu, uses Baidu credentials, and caches an access token locally.

GuidanceBefore installing, confirm that sending moderated content to Baidu is acceptable, configure a scoped Baidu API key/secret, protect or remove the local token cache when needed, and account for the limited source provenance.

Findings (3)

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.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Agentic Supply Chain Vulnerabilities

SeverityInfoConfidenceHighStatusNote

metadata

Source: unknown; Homepage: none

The registry does not provide a source repository or homepage. The included files are readable and coherent, and there is no install-time execution shown, but provenance is limited.

User impactIt may be harder to independently verify the publisher history or upstream source of the skill.

RecommendationReview the included code before use and prefer a trusted or verifiable source when possible.

Permission boundary

Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.

Identity and Privilege Abuse

SeverityLowConfidenceHighStatusNote

SKILL.md

| BCE_SINAN_AK | 是 | 百度云 API Key | ... | BCE_SINAN_SK | 是 | 百度云 Secret Key | ... 缓存文件位置：`~/.claude/skills/baidu-content-censor/token_cache.json`

The skill requires Baidu cloud credentials and stores an access token cache. This is expected for the Baidu moderation API, but users should recognize the credential and token handling, especially because registry requirements declare no required env vars.

User impactThe skill can use the configured Baidu API credentials and may consume the user's Baidu API quota; a cached access token remains on disk until removed or expired.

RecommendationUse the least-privileged Baidu credentials available, monitor API usage, and delete the token cache if uninstalling or rotating credentials.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Insecure Inter-Agent Communication

SeverityMediumConfidenceHighStatusNote

SKILL.md

文本审核: `https://aip.baidubce.com/rest/2.0/solution/v1/text_censor/v2/user_defined` ... 图像审核: `https://aip.baidubce.com/rest/2.0/solution/v1/img_censor/v2/user_defined` ... 本地图片路径会自动转换为 Base64

The skill sends text, image URLs, or base64-encoded local image contents to Baidu's external moderation endpoints. This is central to the stated purpose and disclosed, but it is a third-party data flow.

User impactBaidu receives the content submitted for moderation, including local image bytes if a local image path is used.

RecommendationOnly submit text or images that you are comfortable sending to Baidu and that comply with your privacy or organizational policies.