Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Alicloud Security Cloudfw
v1.0.3Manage Alibaba Cloud Cloud Firewall (Cloudfw) via OpenAPI/SDK. Use whenever the user requests firewall policy/resource operations, change management, status...
⭐ 0· 1.1k·2 current·2 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The name/description match the code and SKILL.md: this is an Alibaba Cloud Cloudfw management helper. However, SKILL.md explicitly instructs use of ALICLOUD_ACCESS_KEY_ID / ALICLOUD_ACCESS_KEY_SECRET and ~/.alibabacloud/credentials, yet the registry metadata declares no required env vars or config paths. That discrepancy is unexpected and reduces transparency about what privileges the skill will need at runtime.
Instruction Scope
The SKILL.md directs the agent to perform discovery, SDK/OpenAPI calls (including Create/Update/Modify operations) and to use credentials from env vars or the shared credentials file. The included script itself only fetches public API metadata, but the instructions explicitly authorize mutating operations and accessing credential sources (env vars, ~/.alibabacloud/credentials). Those file/env accesses are not reflected in the skill's declared requirements and could lead to credential use that the registry metadata doesn't make obvious.
Install Mechanism
No install spec; the skill is instruction-first and ships a small Python script that fetches public metadata from api.aliyun.com and writes outputs to output/alicloud-security-cloudfw/. No archives or external installers are downloaded or executed.
Credentials
SKILL.md asks for Alibaba Cloud access key/secret and optional region and for reading the shared credentials file, but the skill metadata lists no required env vars or config paths. Requesting full access keys for a skill that could be used only for discovery is reasonable in some contexts, but the missing declaration is disproportionate and reduces user ability to enforce least privilege. The SKILL.md also instructs to include key parameters (region/resource id/time range) in output artifacts, which could leak sensitive identifiers if outputs are shared.
Persistence & Privilege
The skill does not request always:true and does not modify other skills or system-wide settings. It writes outputs under its own output directory per the docs, which is normal. There is no install-time persistence mechanism.
What to consider before installing
This skill appears to be a legitimate Alibaba Cloud Cloudfw helper, but there are transparency gaps you should address before installing or running it:
- The SKILL.md expects ALICLOUD_ACCESS_KEY_ID / ALICLOUD_ACCESS_KEY_SECRET and a ~/.alibabacloud/credentials file, yet the registry metadata declares no required credentials — ask the publisher to correct the metadata or explicitly confirm what credentials will be used.
- Treat credentials cautiously: provide least-privilege keys (ideally read-only when you first test), and do not expose full admin keys unless you understand and trust the skill.
- Because the instructions permit mutating API calls (Create/Update/Modify), require the skill to prompt for explicit user confirmation before performing any non-read-only operation.
- The included script only fetches public API metadata from api.aliyun.com and is benign, but the agent runtime (per SKILL.md) may invoke SDKs that use credentials. Verify or request that the skill document a safe default (e.g., dry-run/read-only mode) and a clear confirmation step for changes.
- Confirm where outputs will be saved (output/alicloud-security-cloudfw/) and avoid sharing those artifacts if they contain resource identifiers or timestamps you consider sensitive.
- Because the source/homepage is unknown, consider reviewing the full skill code and SKILL.md locally, and run it first in an isolated environment with limited credentials.
If the publisher updates the registry metadata to declare the required env vars/config paths and adds an explicit confirmation flow for mutating operations, that would increase confidence; until then, proceed cautiously.Like a lobster shell, security has layers — review code before you run it.
latestvk972c2c8er11mm092sh493wh1n82qvqn
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
