v1.0.2

Bic Qa - 佰晟问答

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 8:28 AM.

Analysis

This is a coherent instruction-only BIC-QA API integration, but it uses a user-provided API key and sends the user’s question to BIC-QA’s external API.

GuidanceBefore installing, confirm you trust BIC-QA with the questions you will send, store the API key securely, and avoid putting secrets or confidential system details into prompts. The artifacts do not show malicious behavior or hidden code.

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.

Agent Goal Hijack

SeverityInfoConfidenceHighStatusNote

SKILL.md

成功响应：JSON，通常含 `result` 字段。**请仅基于 `result` 与用户问题组织回答**，并遵守其中关于版本、措辞与结构的说明。

The skill makes the API result authoritative for the final answer. This is normal for a knowledge-base skill, but the agent should keep any returned instructions limited to answering the user’s specific question.

User impactThe answer quality and wording depend on the external API response rather than the model’s independent knowledge.

RecommendationUse the API result as task-specific reference material, and do not treat returned text as permission to ignore the user’s request or perform unrelated actions.

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

集成层或 Agent 在发请求前需能读到 Key，并组装为 **`Authorization: Bearer <你的_API_Key>`**。... Agent 会按优先级依次尝试：环境变量 → 配置文件。

The skill requires an API key and instructs the agent to read it from an environment variable or local config file before calling BIC-QA. This is expected for the service, but it is still account credential use.

User impactAnyone who can read or misuse the API key may be able to use the user’s BIC-QA account/API quota.

RecommendationUse a dedicated BIC-QA API key, keep the file permissions restrictive, avoid sharing it, and rotate it if it may have been exposed.

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

SeverityLowConfidenceHighStatusNote

SKILL.md

curl -s -X POST "https://api.bic-qa.com/skills/qa" ... -d '{"question":"QUESTION","dbtype":"DBTYPE"}'

The skill sends the user’s question and database/topic type to an external provider endpoint. The endpoint is disclosed and purpose-aligned, but user-provided content leaves the local agent context.

User impactQuestions may include proprietary system details or operational information that will be sent to BIC-QA’s API.

RecommendationAvoid including secrets, customer data, credentials, or highly sensitive infrastructure details in questions unless you are comfortable sending them to the provider.