TencentCloud QuestionMark OCR
Analysis
The skill coherently calls Tencent Cloud OCR to grade user-provided exam images or PDFs, but users should notice the Tencent Cloud credentials, third-party data processing, and manual SDK install.
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.
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.
依赖:`tencentcloud-sdk-python`(通过 `pip install tencentcloud-sdk-python` 安装)
The skill relies on a manually installed, unpinned Python SDK dependency. This is normal for a Tencent Cloud API client, but unpinned installs can change over time.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
secret_id = os.environ.get("TENCENTCLOUD_SECRET_ID") ... secret_key = os.environ.get("TENCENTCLOUD_SECRET_KEY")The script uses Tencent Cloud API credentials from environment variables to act on the user's cloud account. This is expected for the integration, but the registry metadata says no required env vars or primary credential.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
req.ImageUrl = args.image_url ... req.ImageBase64 = load_image_base64(args.image_base64) ... resp = client.SubmitQuestionMarkAgentJob(req)
The skill sends a user-provided image URL or Base64/file-derived content to Tencent Cloud for OCR grading. This is the core purpose, but it means exam images, handwriting, and answer content leave the local environment.
