Scrapbook-Style Illustration Inserter
PassAudited by VirusTotal on May 12, 2026.
Findings (1)
The skill is classified as suspicious due to the potential for shell injection. The `SKILL.md` instructs the OpenClaw agent to execute `python3 scripts/generate.py` with a dynamically generated image description (derived from user input and a system prompt) as an argument. While the instructions show the argument enclosed in quotes, a robust agent implementation is critical to prevent shell injection if the generated description contains shell metacharacters or malformed quotes. The `scripts/generate.py` itself broadly searches for API keys across environment variables and various config/`.env` files, which, while intended for flexibility, could be a concern in a compromised environment. However, there is no evidence of intentional malicious behavior such as data exfiltration to unauthorized endpoints, persistence mechanisms, or obfuscation within the provided files.
