Playwright for coding agents. Test that your skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, A/B experiments, CI gates.
- capability exposure inferred + 35
- tool safety inferred + 12
- trust mitigators mixed − 3
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
grade last moved 4d ago · see ecosystem CVEs →
No known CVEs for this server.
- high dangerous code
dynamic exec: unsafe yaml.load(), eval()/exec()
analyzed commit d960de1 · analyzer v33 · 14m ago
skills & prompt files 14
- agent-rules UiPath-coder_eval-d960de1/.claude/commands/coder-eval-code-review-full.md
- agent-rules UiPath-coder_eval-d960de1/.claude/commands/coder-eval-code-review-wf.md
- agent-rules UiPath-coder_eval-d960de1/.claude/commands/coder-eval-code-review.md
- agent-rules UiPath-coder_eval-d960de1/.claude/commands/coder-eval-create-plan.md
- agent-rules UiPath-coder_eval-d960de1/.claude/commands/coder-eval-implement-plan.md
- agent-rules UiPath-coder_eval-d960de1/.claude/commands/coder-eval-review.md
- agent-rules UiPath-coder_eval-d960de1/.claude/notes/agents.md
- agent-rules UiPath-coder_eval-d960de1/CLAUDE.md
- skill UiPath-coder_eval-d960de1/plugins/coder-eval/skills/analyze/SKILL.md
- skill UiPath-coder_eval-d960de1/plugins/coder-eval/skills/check-skill/SKILL.md
- skill UiPath-coder_eval-d960de1/plugins/coder-eval/skills/ci/SKILL.md
- skill UiPath-coder_eval-d960de1/plugins/coder-eval/skills/init/SKILL.md
- skill UiPath-coder_eval-d960de1/plugins/coder-eval/skills/lint-tasks/SKILL.md
- skill UiPath-coder_eval-d960de1/plugins/coder-eval/skills/task/SKILL.md
danger signals3
- dynamic code execution unsafe yaml.load() UiPath-coder_eval-d960de1/tests/lint/doc_indexes.py :82
return yaml.load(mkdocs_path.read_text(encoding="utf-8"), Loader=_NavLoader) - dynamic code execution unsafe yaml.load() UiPath-coder_eval-d960de1/tests/test_custom_lint.py :1285
yaml.load("x: !!python/object/apply:os.system ['echo hi']", Loader=_Probe) - dynamic code execution eval()/exec() UiPath-coder_eval-d960de1/tests/test_sandbox_record_cli.py :485
exec(compile(source, "uip", "exec"), namespace)
[](https://mcpobservatory.com/servers/github:UiPath/coder_eval/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of UiPath.