Ecm Perchance Image
v1.0.0Generates images from text prompts using Perchance.org API with options for orientation and multiple image support.
⭐ 0· 89·1 current·1 all-time
byEvstratios Moraites@evstratios
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name/description match the observed behavior: the code posts prompt+orientation JSON to a Perchance.org endpoint and displays returned image data. The requested resources (none) are appropriate for this purpose.
Instruction Scope
SKILL.md and the Python implemention restrict actions to collecting a prompt, calling the Perchance API, and rendering an image. However, the instructions and code will transmit user-provided prompts to an external endpoint (expected for this skill but a privacy consideration). The SKILL.md references running under OpenClaw and the code provides a terminal-mode entrypoint.
Install Mechanism
There is no install spec (lowest risk), but the code depends on external Python packages (PyQt5, requests) which are not declared. The missing dependency declarations mean users may need to install GUI and networking libraries manually; this is an operational/quality issue rather than an incoherence.
Credentials
The skill requests no environment variables, credentials, or config paths. The external network call goes only to the stated Perchance endpoint, which is proportionate to the described function.
Persistence & Privilege
always is false and the skill does not request persistent or system-wide privileges. It does not modify other skills or system configuration.
Assessment
This skill appears to be what it says: it sends your prompts to https://perchance.org/new-image-gen-by-rs118 and displays returned image data. Before installing/using:
- Don’t send sensitive or private data in prompts (they will be transmitted to an external service).
- The Python file requires PyQt5 and requests but the package/dependency list is missing; install those in a safe environment if you want to run it.
- The included GUI code has multiple API/typing mistakes and will likely crash or behave incorrectly; treat it as prototype code and review/fix before trusting it.
- If you’re concerned about privacy or network exfiltration, run the skill in a sandboxed environment or request a version that logs network calls and has clearer dependency/install instructions.
If you want, I can point out the specific code issues to fix or make a safer, headless (non-GUI) variant that you can review first.Like a lobster shell, security has layers — review code before you run it.
latestvk978xefcvtvpq3pjcxecensfxs839zbn
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
