Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward skill-authoring helper with some local filesystem guidance, and I did not find hidden execution, network access, credential handling, or destructive behavior.
Install this if you want an agent helper for creating and packaging OpenClaw skills. Be aware that skill creation writes persistent files under the OpenClaw workspace, and the bundled list_skills.py utility can read installed skills' SKILL.md metadata and print their names, descriptions, and paths if invoked.
A mismatch between the declared purpose and the actual behavior is security-relevant because users may invoke the skill expecting authoring/package operations while it also performs discovery or metadata inspection of installed skills and filesystem locations. That expands the effective data access surface and can enable unintended enumeration of local environment details under a misleading description.
The skill instructs use of local Python scripts and references concrete filesystem paths, but it does not declare any explicit tool scope such as allowed tools or permissions. In a skill-authoring context, undeclared file-read capability weakens least-privilege boundaries and can cause the agent to access workspace or installed-skill files beyond what users would reasonably expect.
The trigger conditions are very broad, including generic phrases like creating, building, packaging, or auditing skills in multiple languages. Overbroad activation increases the chance the skill runs in contexts the user did not intend, which is especially risky for a skill that can initialize files, invoke scripts, and package artifacts.
The template instruction says to "Include Chinese triggers too," which mandates a specific language requirement rather than offering language choice based on user preference. This is a natural-language policy issue because it forces locale/language behavior without opt-in or justification.
