Long-running AI agents coordinating over their human's own Fulcra account — shared bus, cross-model reviews, session continuity, load balancing. Unofficial, MIT.
- 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.
grade last moved 3d ago · see ecosystem CVEs →
- A · 0 → C · 56
No known CVEs for this server.
- high dangerous code
dynamic exec: eval()/exec(), unsafe yaml.load()
analyzed commit 8afb5a7 · analyzer v33 · 3d ago
skills & prompt files 28
- agent-rules ashfulcra-fulcra-tools-8afb5a7/AGENTS.md
- agent-rules ashfulcra-fulcra-tools-8afb5a7/packages/attention/AGENTS.md
- skill ashfulcra-fulcra-tools-8afb5a7/packages/csv-importer/skills/fulcra-csv/SKILL.md
- agent-rules ashfulcra-fulcra-tools-8afb5a7/packages/fulcra-continuity/AGENTS.md
- skill ashfulcra-fulcra-tools-8afb5a7/packages/fulcra-prefs/skill/SKILL.md
- skill ashfulcra-fulcra-tools-8afb5a7/packages/fulcra-vault/skill/SKILL.md
- agent-rules ashfulcra-fulcra-tools-8afb5a7/packages/media-helpers/AGENTS.md
- skill ashfulcra-fulcra-tools-8afb5a7/packages/media-helpers/skills/fulcra-media/SKILL.md
- skill ashfulcra-fulcra-tools-8afb5a7/packages/netflix-skill/skills/fulcra-netflix/SKILL.md
- skill ashfulcra-fulcra-tools-8afb5a7/skills/coordinator-discipline/SKILL.md
- skill ashfulcra-fulcra-tools-8afb5a7/skills/fulcra-agent-atc/SKILL.md
- skill ashfulcra-fulcra-tools-8afb5a7/skills/fulcra-agent-automation/SKILL.md
- skill ashfulcra-fulcra-tools-8afb5a7/skills/fulcra-agent-cloud-coordinator/SKILL.md
- skill ashfulcra-fulcra-tools-8afb5a7/skills/fulcra-agent-continuity/SKILL.md
- skill ashfulcra-fulcra-tools-8afb5a7/skills/fulcra-agent-directives/SKILL.md
- skill ashfulcra-fulcra-tools-8afb5a7/skills/fulcra-agent-durable-state/SKILL.md
- skill ashfulcra-fulcra-tools-8afb5a7/skills/fulcra-agent-forge/SKILL.md
- skill ashfulcra-fulcra-tools-8afb5a7/skills/fulcra-agent-health/SKILL.md
- skill ashfulcra-fulcra-tools-8afb5a7/skills/fulcra-agent-operator/SKILL.md
- skill ashfulcra-fulcra-tools-8afb5a7/skills/fulcra-agent-presence/SKILL.md
- skill ashfulcra-fulcra-tools-8afb5a7/skills/fulcra-agent-reconcile/SKILL.md
- skill ashfulcra-fulcra-tools-8afb5a7/skills/fulcra-agent-review/SKILL.md
- skill ashfulcra-fulcra-tools-8afb5a7/skills/fulcra-agent-roles/SKILL.md
- skill ashfulcra-fulcra-tools-8afb5a7/skills/fulcra-agent-tasks/SKILL.md
- skill ashfulcra-fulcra-tools-8afb5a7/skills/fulcra-content-review/SKILL.md
- skill ashfulcra-fulcra-tools-8afb5a7/skills/fulcra-fde/SKILL.md
- skill ashfulcra-fulcra-tools-8afb5a7/skills/fulcra-lab-results/SKILL.md
- skill ashfulcra-fulcra-tools-8afb5a7/skills/sealed-secrets/SKILL.md
danger signals2
- dynamic code execution eval()/exec() ashfulcra-fulcra-tools-8afb5a7/packages/coord-fold/tests/test_ship_check.py :512
ns = {"__name__": "attest_lib"}; exec(ship_check.ATTEST, ns) - dynamic code execution unsafe yaml.load() ashfulcra-fulcra-tools-8afb5a7/packages/task-sync/fulcra_task_sync/documents.py :60
data = yaml.load(header, Loader=StrictLoader)
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:ashfulcra/fulcra-tools/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 ashfulcra.