Agent repository for scientific research, including knowledge, feed ranking, and experiment tracking MCPs
- capability exposure inferred + 35
- tool safety inferred + 10
inferred
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 10h ago · see ecosystem CVEs →
No known CVEs for this server.
- medium dangerous code
dynamic exec: __import__()
- medium toxic flow (lethal trifecta)
lethal trifecta reachable across this server's tool + source surface: private-data access + untrusted-content ingestion + network exfil (a leg is proven only in the analyzed source)
analyzed commit 5f3e5bf · analyzer v33 · 2d ago
skills & prompt files 19
- agent-rules mgoldey-attestation-5f3e5bf/.claude/agents/attestation-feed.md
- agent-rules mgoldey-attestation-5f3e5bf/.claude/agents/attestation-knowledge.md
- agent-rules mgoldey-attestation-5f3e5bf/.claude/agents/attestation-provenance.md
- agent-rules mgoldey-attestation-5f3e5bf/.claude/agents/attestation-symbolic.md
- agent-rules mgoldey-attestation-5f3e5bf/CLAUDE.md
- agent-rules mgoldey-attestation-5f3e5bf/docs/guides/agents.md
- prompt-file mgoldey-attestation-5f3e5bf/evals/prompts/transfer-2026-08-27.md
- prompt-file mgoldey-attestation-5f3e5bf/evals/prompts/transfer-2026-08-28.md
- prompt-file mgoldey-attestation-5f3e5bf/evals/prompts/transfer-feed-2026-09-03.md
- prompt-file mgoldey-attestation-5f3e5bf/evals/prompts/transfer-symbolic-2026-09-03.md
- prompt-file mgoldey-attestation-5f3e5bf/evals/prompts/write-side-2026-09-01.md
- prompt-file mgoldey-attestation-5f3e5bf/evals/prompts/write-side-2026-09-02.md
- skill mgoldey-attestation-5f3e5bf/src/attestation/skills/attestation-annotate/SKILL.md
- skill mgoldey-attestation-5f3e5bf/src/attestation/skills/attestation-feed/SKILL.md
- skill mgoldey-attestation-5f3e5bf/src/attestation/skills/attestation-knowledge/SKILL.md
- skill mgoldey-attestation-5f3e5bf/src/attestation/skills/attestation-provenance/SKILL.md
- skill mgoldey-attestation-5f3e5bf/src/attestation/skills/attestation-record/SKILL.md
- skill mgoldey-attestation-5f3e5bf/src/attestation/skills/attestation-setup/SKILL.md
- skill mgoldey-attestation-5f3e5bf/src/attestation/skills/attestation-symbolic/SKILL.md
danger signals1
- dynamic code execution __import__() mgoldey-attestation-5f3e5bf/tests/test_package_surface.py :46
__import__(f"attestation.{name}")
[](https://mcpobservatory.com/servers/github:mgoldey/attestation/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 mgoldey.