Webapp Testing Anthropic

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing...

This skill appears to do what it says (local Playwright testing) but take precautions before running it: 1) Inspect the included scripts (especially scripts/with_server.py) yourself — do not accept the SKILL.md suggestion to skip reading the source. The helper starts user-provided commands using shell=True, so malformed or malicious command strings could run arbitrary shell code. 2) Ensure Playwright, its browser binaries, and any node/npm tooling you need are installed — the skill does not declare or install these dependencies. 3) Run the scripts in an isolated environment (container or VM) when first testing, and avoid passing sensitive credentials in server command arguments. 4) Note where example scripts write files (/mnt/user-data/outputs, /tmp) and ensure those locations are appropriate. If you need to rely on this skill in production or give it broader access, ask the author for explicit dependency and security documentation, or only use the code after manual review.

Type: OpenClaw Skill Name: webapp-testing-anthropic Version: 1.0.0 The skill bundle contains a helper script, `scripts/with_server.py`, which utilizes `subprocess.Popen(shell=True)` to execute arbitrary shell commands, introducing a significant shell injection vulnerability. Additionally, the `SKILL.md` file includes explicit instructions directing the AI agent to avoid reading the source code of the provided scripts, falsely claiming they are "very large" to justify this behavior. This instruction is a common prompt-injection tactic used to evade security inspection of the code the agent is expected to execute.