v1.0.0

身份证二要素核验 - 聚合数据

ReviewClawScan verdict for this skill. Analyzed May 1, 2026, 8:21 AM.

Analysis

This skill does what it claims, but it handles very sensitive identity data and the included script sends the API key, name, and ID number over plain HTTP and may print unmasked personal data.

GuidanceReview carefully before installing. This skill is aligned with its stated identity-verification purpose, but it handles national ID data. Do not use it until the API call is changed to HTTPS and the script stops printing raw unmasked identity fields.

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.

Human-Agent Trust Exploitation

SeverityMediumConfidenceHighStatusConcern

scripts/idcard_verify.py

"realname": res.get("realname", realname),
"idcard": res.get("idcard", idcard),
...
print(json.dumps(result, ensure_ascii=False, indent=2))

Although the skill documentation instructs the agent to display desensitized results, the script prints the raw result object after the masked output; that object can include the full name and ID number.

User impactFull identity details may appear in the chat, tool output, logs, or downstream agent context even when the user expects masking.

RecommendationRemove the raw JSON print or mask the `realname` and `idcard` fields before output; make the documentation match the actual output behavior.

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

requires":{"bins":["python3"],"env":["JUHE_IDCARD_VERIFY_KEY"]},"primaryEnv":"JUHE_IDCARD_VERIFY_KEY"

The skill requires a Juhe API credential, which is expected for this API integration but gives the script authority to spend or use the user's Juhe account quota.

User impactUsing this skill consumes the user's Juhe API quota and depends on keeping the API key private.

RecommendationUse a dedicated, least-privilege Juhe key if available, monitor quota usage, and do not paste the key into shared chats or logs.

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

SeverityHighConfidenceHighStatusConcern

scripts/idcard_verify.py

API_URL = "http://op.juhe.cn/idcard/query"
...
params = urllib.parse.urlencode({
        "key": api_key,
        "realname": realname,
        "idcard": idcard,
    })

The script sends the API key, real name, and ID number to the provider using plain HTTP query parameters, exposing highly sensitive identity data and the credential to network interception or logging.

User impactA user's name, national ID number, and Juhe API key could be exposed outside the intended secure channel.

RecommendationChange the script to use the HTTPS endpoint, avoid exposing secrets in URLs where possible, and clearly warn users that their identity data is sent to Juhe for verification.