Security risk report for @forgecat/openai_skills_playwright v0.0.11
Source Integrity
Low
Profile is sourced from OpenAI's official skills repository (https://github.com/openai/skills) with clear attribution and Apache-2.0 license.
Metadata includes verifiable commit hash and timestamp, indicating transparent provenance.
Agent Intent
Low
Content describes legitimate browser automation workflows (navigation, form filling, snapshots, screenshots) without injecting hidden instructions or attempting to manipulate the AI.
No directives to read credentials, exfiltrate data, reveal system prompts, or install malicious payloads.
Guidance recommends standard Playwright CLI patterns and best practices (snapshot before refs, re-snapshot on stale refs, prefer CLI over eval) — these are security-conscious guardrails, not poisoning.
Details
Evidence
"Prefer the wrapper script so the CLI works even when it is not globally installed."
"Always snapshot before referencing element ids like `e12`. Re-snapshot when refs seem stale."
"Prefer explicit commands over `eval` and `run-code` unless needed."
Permissions
Low
No tools or MCP servers are declared in this profile; it is purely instructional documentation for using Playwright CLI.
The wrapper script invokes `npx --package @playwright/cli playwright-cli`, which is scoped to browser automation and does not request file system mutations, shell execution, or network access beyond the target website.
ForgeCat