github Python analyzed eb7304c deep scan · partial (174/2,245 files)

ThreeMoonsLab/agents-shipgate

v1.0.0

The deterministic merge gate for AI-generated agent capability changes — a local-first, static Tool-Use Readiness review for MCP, OpenAPI, and SDK tool surfaces. Open-source CLI + GitHub Action.

maintainer: ThreeMoonsLab
licence: Apache-2.0
first seen: 2026-06-04
last seen: 2026-09-18
releases · 30d: 3
short id

risk 51/100 · heuristic grade

C elevated inferred analyzer v33 (current)

capability exposure inferred + 22
recent drift inferred + 20
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 1w ago · see ecosystem CVEs →

risk trajectory 2 movements

11w ago C · 43 → C · 51
12w ago A · 0 → C · 43

capability exposure grade factor +22

Inferred surface — each links to servers holding it:

vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 1 findings · grade factor +12

high dangerous code

committed secret: OpenAI key, GitHub token, Slack token, GitHub fine-grained PAT · dynamic exec: __import__(), unsafe yaml.load(), eval()/exec(), pickle.loads(), __import__ sink

skills & danger signals github-tarball

prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed commit eb7304c · analyzer v33 · 22h ago

skills & prompt files 58

danger signals19

dynamic code execution __import__() ThreeMoonsLab-agents-shipgate-eb7304c/benchmark/cold-start/replay.py :44 return __import__(name)
dynamic code execution unsafe yaml.load() ThreeMoonsLab-agents-shipgate-eb7304c/src/agents_shipgate/cli/apply_patches.py :753 data = yaml.load(text) or {}
dynamic code execution __import__() ThreeMoonsLab-agents-shipgate-eb7304c/src/agents_shipgate/cli/self_check.py :144 __import__(module_name)
dynamic code execution eval()/exec() ThreeMoonsLab-agents-shipgate-eb7304c/tests/test_environment.py :140 exec(compile(path.read_text(encoding="utf-8"), str(path), "exec"), namespace)
dynamic code execution pickle.loads() ThreeMoonsLab-agents-shipgate-eb7304c/tests/test_init_scaffold_disclosure.py :812 pickle.loads(pickle.dumps(rendered)),
dynamic code execution eval()/exec() ThreeMoonsLab-agents-shipgate-eb7304c/tests/test_install_hooks.py :1158 exec(compile(code, str(script), "exec"), namespace)
dynamic code execution eval()/exec() ThreeMoonsLab-agents-shipgate-eb7304c/tests/test_instruction_structure_hooks.py :16 exec(compile(_hook_script_text(), "generated-hook.py", "exec"), namespace)
dynamic code execution __import__ sink ThreeMoonsLab-agents-shipgate-eb7304c/tests/test_toolkit_bounds_check.py :91 env = dict(__import__("os").environ)
over-broad OAuth scope delete_repo ThreeMoonsLab-agents-shipgate-eb7304c/tests/test_mcp_manifest.py :436 "github": {"command": "gh", "tools": {"search": {}, "delete_repo": {}}}
committed secret OpenAI key ThreeMoonsLab-agents-shipgate-eb7304c/tests/harness/fixtures/mock_run_bad/transcript.jsonl :1 sk-pro…(30 chars, redacted)
committed secret OpenAI key ThreeMoonsLab-agents-shipgate-eb7304c/tests/harness/test_infrastructure_failures.py :344 sk-pro…(29 chars, redacted)
committed secret OpenAI key ThreeMoonsLab-agents-shipgate-eb7304c/tests/test_declaration_review.py :761 sk-aaa…(27 chars, redacted)
committed secret OpenAI key ThreeMoonsLab-agents-shipgate-eb7304c/tests/test_n8n.py :1245 sk-aaa…(27 chars, redacted)
committed secret GitHub token ThreeMoonsLab-agents-shipgate-eb7304c/tests/test_n8n.py :1248 ghp_aa…(40 chars, redacted)
committed secret Slack token ThreeMoonsLab-agents-shipgate-eb7304c/tests/test_n8n.py :1250 xoxb-a…(25 chars, redacted)
committed secret OpenAI key ThreeMoonsLab-agents-shipgate-eb7304c/tests/test_privacy.py :25 sk-aaa…(27 chars, redacted)
committed secret GitHub fine-grained PAT ThreeMoonsLab-agents-shipgate-eb7304c/tests/test_privacy.py :59 github…(47 chars, redacted)
committed secret Slack token ThreeMoonsLab-agents-shipgate-eb7304c/tests/test_privacy.py :60 xoxa-2…(23 chars, redacted)
committed secret GitHub token ThreeMoonsLab-agents-shipgate-eb7304c/tests/test_privacy.py :236 ghp_aa…(40 chars, redacted)

other grade factors evidence elsewhere

recent drift +20 capability drift →

embed badge readme-ready

[![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:ThreeMoonsLab/agents-shipgate/badge.svg)](https://mcpobservatory.com/servers/github:ThreeMoonsLab/agents-shipgate/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 ThreeMoonsLab.

ThreeMoonsLab/agents-shipgate

skills & prompt files 58

danger signals19

Navigate

Stream

Features

Display