Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
ProcessOn Diagrams Generator
v2.3.0帮助用户生成专业、美观、可继续编辑的图形，包括流程图、时序图、架构图、网络拓扑图、ER 图、组织结构图、时间轴、信息图、金字塔图，以及草图重绘。当用户提到“生成图”、“画图”、“流程图”、“架构分析”、“拓扑图”、“重绘草图”等需求时应触发本技能。Also use this skill when the user...
⭐ 0· 87·0 current·0 all-time
byying zhang @po@leilizhang
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The skill's code and SKILL.md clearly require a PROCESSON_API_KEY and expect python3 (SKILL.md header lists python3), and the embedded script calls smart.processon.com endpoints and saves images locally. However, the registry metadata lists no required environment variables or required binaries — this mismatch between declared metadata and actual needs is inconsistent and could mislead users about what credentials or runtimes are required.
Instruction Scope
The SKILL.md stays on-topic for generating diagrams, but it instructs the agent to: (a) prioritize reading entry files, routes, core configs and key modules when doing architecture analysis (i.e., access local project files), and (b) always display the full DSL, the editor URL, and any image links/paths in plain text before finishing. Reading local project files is coherent for 'architecture analysis' but expands the skill's scope to access local files; the enforced output rules (must immediately print DSL and file/URL info) may cause sensitive local paths or content to be revealed in responses.
Install Mechanism
There is no automated install spec in the registry (instruction-only install), which is lower risk than arbitrary downloads. The skill does include a bundled Python script (scripts/processon_api_client.py) and README suggesting an npx-based installation from a GitHub repo; no external, untrusted binary downloads or URL-shortened installers are present in the provided files.
Credentials
The skill legitimately needs a ProcessOn API key to call smart.processon.com and the SKILL.md repeatedly instructs users to set PROCESSON_API_KEY in the agent's runtime environment. But the registry metadata does not declare this required environment variable. Additionally the script may read auxiliary env vars (PROCESSON_OUTPUT_MODE, PROCESSON_STREAM_STYLE). The required credential is proportional to the feature, but the missing declaration is an inconsistency and a potential surprise to users.
Persistence & Privilege
The skill does not request always:true, does not claim to modify other skills or system-wide settings, and is user-invocable. It does write generated images to a local outputs directory when run, which is typical for a generation tool but not a system-wide persistence or privilege escalation request.
What to consider before installing
Before installing: 1) Expect to provide a PROCESSON_API_KEY (skilled is unusable without it) — create and scope that key carefully and don't reuse high-privilege credentials. 2) The metadata in the registry does not list the required env var or python3 dependency even though SKILL.md and the included script use them — treat that as a red flag and verify the source. 3) The skill's runtime instructs the agent to read local project files for architecture analysis and to always print the full DSL, editor URL, and any image links or local saved file paths; if your codebase or environment contains secrets, be cautious about allowing the skill broad filesystem access. 4) The included Python script calls smart.processon.com and will save images under outputs/processon in the working directory; review the script locally before executing and consider running it in an isolated environment (container or VM). 5) If you decide to proceed, inspect the script for any unexpected network endpoints or behavior, limit the API key scope if possible, and test in a throwaway environment first.Like a lobster shell, security has layers — review code before you run it.
latestvk97eesa9zatakt4kp3ba4gy5vd84vxr2
License
MIT-0
Free to use, modify, and redistribute. No attribution required.