prompt-engineer-toolkit

Analyzes and rewrites prompts for better AI output, creates reusable prompt templates for marketing use cases (ad copy, email campaigns, social media), and s...

This skill appears to do what it says, but review before use: (1) Inspect the scripts yourself — they run locally and are readable. (2) Be careful when supplying --runner-cmd: the script will execute whatever command you provide (so avoid embedding secrets or using networked commands you don't trust). (3) The versioner writes a local JSONL file (.prompt_versions.jsonl by default); ensure it is stored in a safe directory and that sensitive prompt content (PII, secrets) is handled appropriately. (4) If you plan to let an autonomous agent call this skill, restrict or validate any runner_cmd the agent could construct to avoid accidental execution of arbitrary system/network commands. (5) If you want additional assurance, run the tools in an isolated environment or container and/or have an administrator review the code before deployment.

Type: OpenClaw Skill Name: prompt-engineer-toolkit Version: 1.0.0 The toolkit provides functional prompt engineering utilities, but `scripts/prompt_tester.py` contains a high-risk capability via the `--runner-cmd` parameter. This feature uses `subprocess.run` to execute arbitrary shell commands constructed from user-provided templates, which could be exploited for command injection or arbitrary code execution if the agent is manipulated into using a malicious runner or processing untrusted input. While this behavior is aligned with the tool's stated purpose of testing prompts against external CLIs, it represents a significant security risk without clear evidence of intentional malice.