Watercooler: your team's shared reasoning layer for agentic coding. Preserve the "why" around your code.
- capability exposure inferred + 35
- recent drift inferred + 12
- 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.
graded 9m ago · see ecosystem CVEs →
- B · 32 → C · 56
No known CVEs for this server.
- high dangerous code
committed secret: Slack token · dynamic exec: pickle.loads()
analyzed commit a5efa89 · analyzer v28 · 1d ago
skills & prompt files 21
- skill mostlyharmless-ai-watercooler-a5efa89/plugins/claude/watercooler/skills/find-related/SKILL.md
- skill mostlyharmless-ai-watercooler-a5efa89/plugins/claude/watercooler/skills/recall/SKILL.md
- skill mostlyharmless-ai-watercooler-a5efa89/plugins/claude/watercooler/skills/search-threads/SKILL.md
- skill mostlyharmless-ai-watercooler-a5efa89/plugins/claude/watercooler/skills/threads/SKILL.md
- skill mostlyharmless-ai-watercooler-a5efa89/plugins/claude/watercooler/skills/update-agent-context/SKILL.md
- skill mostlyharmless-ai-watercooler-a5efa89/plugins/claude/watercooler/skills/watercooler-health/SKILL.md
- skill mostlyharmless-ai-watercooler-a5efa89/plugins/claude/watercooler/skills/watercooler-onboarding/SKILL.md
- skill mostlyharmless-ai-watercooler-a5efa89/plugins/codex/watercooler/skills/find-related/SKILL.md
- skill mostlyharmless-ai-watercooler-a5efa89/plugins/codex/watercooler/skills/recall/SKILL.md
- skill mostlyharmless-ai-watercooler-a5efa89/plugins/codex/watercooler/skills/search-threads/SKILL.md
- skill mostlyharmless-ai-watercooler-a5efa89/plugins/codex/watercooler/skills/threads/SKILL.md
- skill mostlyharmless-ai-watercooler-a5efa89/plugins/codex/watercooler/skills/update-agent-context/SKILL.md
- skill mostlyharmless-ai-watercooler-a5efa89/plugins/codex/watercooler/skills/watercooler-health/SKILL.md
- skill mostlyharmless-ai-watercooler-a5efa89/plugins/codex/watercooler/skills/watercooler-onboarding/SKILL.md
- skill mostlyharmless-ai-watercooler-a5efa89/skills/find-related/SKILL.md
- skill mostlyharmless-ai-watercooler-a5efa89/skills/recall/SKILL.md
- skill mostlyharmless-ai-watercooler-a5efa89/skills/search-threads/SKILL.md
- skill mostlyharmless-ai-watercooler-a5efa89/skills/threads/SKILL.md
- skill mostlyharmless-ai-watercooler-a5efa89/skills/update-agent-context/SKILL.md
- skill mostlyharmless-ai-watercooler-a5efa89/skills/watercooler-health/SKILL.md
- skill mostlyharmless-ai-watercooler-a5efa89/skills/watercooler-onboarding/SKILL.md
danger signals4
- dynamic code execution pickle.loads() mostlyharmless-ai-watercooler-a5efa89/tests/integration/test_pat_pilot_chain.py :142
rehydrated = pickle.loads(pickle.dumps(s)) - dynamic code execution pickle.loads() mostlyharmless-ai-watercooler-a5efa89/tests/unit/test_secret_wrapper.py :407
rehydrated = pickle.loads(pickle.dumps(original)) - committed secret Slack token mostlyharmless-ai-watercooler-a5efa89/tests/unit/test_secret_wrapper.py :236
xoxb-s…(15 chars, redacted) - committed secret Slack token mostlyharmless-ai-watercooler-a5efa89/tests/unit/test_security.py :62
xoxb-s…(23 chars, redacted)
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:mostlyharmless-ai/watercooler/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 mostlyharmless-ai.