github analyzed 06be497

Leo-Atienza/atlas-claude

ATLAS — Autonomous Task, Learning, and Agent System. A self-evolving AI operating system for Claude Code. Auto-continuation, smart swarms, self-evolution, and 282 skills.

maintainer: Leo-Atienza
license: MIT
first seen: 2026-06-04
last seen: 2026-06-04
releases · 30d: 0
short id

risk 71/100 · heuristic grade

D high

capability exposureinferred+35
recent driftinferred+12
tool safetyinferred+24

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.

graded 14m ago · see ecosystem CVEs →

risk trajectory 1 movements

2d agoA · 0 → D · 71

capability exposure grade factor +35

Inferred surface — each links to servers holding it:

vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 2 findings · grade factor +24

highdangerous code
dynamic exec: eval()/exec() · suspicious bundled script in 10 file(s)
highhidden prompt content
1 file(s) with hidden prompt content: Leo-Atienza-atlas-claude-06be497/skills/api-routes/SKILL.md (skill-exfil): "secret→sink: `https://api.weather.com/v1/current?city=${city}&key…

skills & danger signals github-tarball

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

analyzed commit 06be497 · analyzer v18 · 11h ago

skills & prompt files 133

⚠ hidden: skill: skill-exfilLeo-Atienza-atlas-claude-06be497/skills/api-routes/SKILL.md:353secret→sink: `https://api.weather.com/v1/current?city=${city}&key=${process.env.WEATHER_API_KEY}`

danger signals11

dynamic code executioneval()/exec()Leo-Atienza-atlas-claude-06be497/plugins/marketplaces/claude-plugins-official/plugins/security-guidance/hooks/security_reminder_hook.py:77exec(`command ${userInput}`)
suspicious bundled scriptsuspicious bundled scriptLeo-Atienza-atlas-claude-06be497/skills/cc-devops/azure-pipelines-validator/scripts/check_security.py:59(re.compile(r'Invoke-WebRequest.*\|\s*(Invoke-Expression|iex)'), 'invoke-web-pipe-iex', 'Download and verify scripts before execution'),
suspicious bundled scriptsuspicious bundled scriptLeo-Atienza-atlas-claude-06be497/skills/cc-devops/dockerfile-generator/scripts/generate_nodejs.sh:117CMD node -e "require('http').get('http://localhost:PORT_NUMBER/health', (r) => {process.exit(r.statusCode === 200 ? 0 : 1)})" || exit 1
suspicious bundled scriptsuspicious bundled scriptLeo-Atienza-atlas-claude-06be497/skills/cc-devops/dockerfile-generator/scripts/generate_python.sh:112CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:PORT_NUMBER/health').read()" || exit 1
suspicious bundled scriptsuspicious bundled scriptLeo-Atienza-atlas-claude-06be497/skills/cc-devops/github-actions-validator/scripts/install_tools.sh:49curl --proto '=https' --tlsv1.2 -sSf https://raw.githubusercontent.com/nektos/act/master/install.sh | bash -s -- -b "${TOOLS_DIR}"
suspicious bundled scriptsuspicious bundled scriptLeo-Atienza-atlas-claude-06be497/skills/cc-devops/helm-validator/scripts/setup_tools.sh:89echo " Linux: curl https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash"
suspicious bundled scriptsuspicious bundled scriptLeo-Atienza-atlas-claude-06be497/skills/skills-archive/cc-devops/azure-pipelines-validator/scripts/check_security.py:59(re.compile(r'Invoke-WebRequest.*\|\s*(Invoke-Expression|iex)'), 'invoke-web-pipe-iex', 'Download and verify scripts before execution'),
suspicious bundled scriptsuspicious bundled scriptLeo-Atienza-atlas-claude-06be497/skills/skills-archive/cc-devops/dockerfile-generator/scripts/generate_nodejs.sh:117CMD node -e "require('http').get('http://localhost:PORT_NUMBER/health', (r) => {process.exit(r.statusCode === 200 ? 0 : 1)})" || exit 1
suspicious bundled scriptsuspicious bundled scriptLeo-Atienza-atlas-claude-06be497/skills/skills-archive/cc-devops/dockerfile-generator/scripts/generate_python.sh:112CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:PORT_NUMBER/health').read()" || exit 1
suspicious bundled scriptsuspicious bundled scriptLeo-Atienza-atlas-claude-06be497/skills/skills-archive/cc-devops/github-actions-validator/scripts/install_tools.sh:49curl --proto '=https' --tlsv1.2 -sSf https://raw.githubusercontent.com/nektos/act/master/install.sh | bash -s -- -b "${TOOLS_DIR}"
suspicious bundled scriptsuspicious bundled scriptLeo-Atienza-atlas-claude-06be497/skills/skills-archive/cc-devops/helm-validator/scripts/setup_tools.sh:89echo " Linux: curl https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash"

other grade factors evidence elsewhere

recent drift+12 capability drift →

embed badge readme-ready

[![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:Leo-Atienza/atlas-claude/badge.svg)](https://mcpobservatory.com/servers/github:Leo-Atienza/atlas-claude/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 Leo-Atienza.

Leo-Atienza/atlas-claude

skills & prompt files 133

danger signals11

Navigate

Stream

Display