Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Image Generator
v1.0.0Generate images via BigModel APIs and send them as chat images (e.g. Feishu). Invoke when user asks to create a single picture with specific style/size.
⭐ 2· 272·0 current·0 all-time
byHongz@henrybao91
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
Name/description match the implementation: the script calls https://open.bigmodel.cn/api/paas/v4/images/generations and requires ZHIPU_API_KEY. That credential is the only declared requirement and is appropriate for the described purpose. Minor mismatch: SKILL.md only documents using an environment variable, whereas the script includes an undocumented fallback that reads TOOLS.md files to find the API key.
Instruction Scope
SKILL.md instructs the agent to run scripts/generate.py and then parse stdout for the saved image path — which is consistent with the script output. However, the script also attempts to read TOOLS.md from multiple locations (including several parent directories) to extract ZHIPU_API_KEY if the env var is not set. That file-reading behavior is not declared in SKILL.md and could access unexpected local files containing secrets. Also note a coding bug: the script uses re.search but does not import the re module, so the fallback path will likely error if used.
Install Mechanism
This is an instruction-only skill with a bundled Python script and no install spec. That minimizes installer risk. The script uses the requests library but the skill does not declare or install Python or requests; ensure runtime has Python and requests available. No remote install downloads or obscure URLs are used.
Credentials
The only required env var declared is ZHIPU_API_KEY (appropriate). But the script additionally searches for ZHIPU_API_KEY inside TOOLS.md files in multiple locations (an undocumented credential fallback). Reading arbitrary TOOLS.md files increases the chance of accidental secret exposure and is not justified or declared in SKILL.md. No other unrelated credentials are requested.
Persistence & Privilege
The skill does not request permanent/always-on privileges (always:false). It writes generated images to disk (workspace paths) and prints the saved path for the agent to attach — this is expected and limited in scope. The skill does not modify other skills or global agent settings.
What to consider before installing
This skill appears to implement the advertised image-generation behavior, but review before enabling: 1) Set ZHIPU_API_KEY explicitly in the agent/tool config rather than relying on the script's undocumented TOOLS.md search — the script will try to read TOOLS.md files in parent/workspace locations which could expose local secrets. 2) Be aware the script expects the requests Python package; ensure the runtime has it. 3) There's a minor bug (missing import re) which will cause the fallback file-read code to fail; that reduces risk of hidden key extraction but also indicates the code was not fully reviewed. 4) If you will run this in a production environment, inspect any TOOLS.md files in your workspace for sensitive data or remove that fallback behavior. 5) If you need greater assurance, ask the publisher for source provenance or a homepage and request they remove or document the TOOLS.md fallback. If you are uncomfortable with the undocumented file access, do not install or run the skill until it's fixed/documented.Like a lobster shell, security has layers — review code before you run it.
latestvk97c48t2djyd8k7b6xj4adh2t982sj2r
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🖼️ Clawdis
EnvZHIPU_API_KEY
Primary envZHIPU_API_KEY