All of my portable Agent Skills with local validation and MCP access
- capability exposure inferred + 16
- 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 3d ago · see ecosystem CVEs →
- C · 37 → C · 45
- A · 0 → C · 37
No known CVEs for this server.
- high dangerous code
dynamic exec: unsafe yaml.load()
analyzed commit 40afe81 · analyzer v33 · 1d ago
skills & prompt files 23
- agent-rules srinitude-skills-40afe81/AGENTS.md
- skill srinitude-skills-40afe81/skills/always-current-datetime/SKILL.md
- skill srinitude-skills-40afe81/skills/by-design/SKILL.md
- skill srinitude-skills-40afe81/skills/dedupe/SKILL.md
- skill srinitude-skills-40afe81/skills/design-like-im-5/SKILL.md
- skill srinitude-skills-40afe81/skills/dtcg-tokens/SKILL.md
- skill srinitude-skills-40afe81/skills/figma-code-connect-design-system/SKILL.md
- skill srinitude-skills-40afe81/skills/goal-prompt/SKILL.md
- skill srinitude-skills-40afe81/skills/logic-audit/SKILL.md
- skill srinitude-skills-40afe81/skills/meaning-preserving-rewrite/SKILL.md
- skill srinitude-skills-40afe81/skills/mobile-first-website-design/SKILL.md
- skill srinitude-skills-40afe81/skills/only-one-interpretation/SKILL.md
- skill srinitude-skills-40afe81/skills/outcome-bounded-work/SKILL.md
- skill srinitude-skills-40afe81/skills/prompt-enhancer/SKILL.md
- skill srinitude-skills-40afe81/skills/reify/SKILL.md
- skill srinitude-skills-40afe81/skills/simplify-skill/SKILL.md
- skill srinitude-skills-40afe81/skills/skill-factory/SKILL.md
- skill srinitude-skills-40afe81/skills/starting-point/SKILL.md
- skill srinitude-skills-40afe81/skills/timebox/SKILL.md
- skill srinitude-skills-40afe81/skills/tool-call-configuration-for/SKILL.md
- skill srinitude-skills-40afe81/skills/visual-design-system-extractor/SKILL.md
- skill srinitude-skills-40afe81/skills/would-agents-actually/SKILL.md
- skill srinitude-skills-40afe81/skills/would-humans-actually/SKILL.md
danger signals5
- dynamic code execution unsafe yaml.load() srinitude-skills-40afe81/evidence/ports/visual-design-system-extractor/native/scripts/validate_design_system_yaml.py :81
return yaml.load(text, Loader=StrictLoader), None - dynamic code execution unsafe yaml.load() srinitude-skills-40afe81/skills/mobile-first-website-design/scripts/validate_skill.py :69
fields = yaml.load(header, Loader=UniqueKeyLoader) - dynamic code execution unsafe yaml.load() srinitude-skills-40afe81/skills/skill-factory/scripts/validate_skill.py :69
fields = yaml.load(header, Loader=UniqueKeyLoader) - dynamic code execution unsafe yaml.load() srinitude-skills-40afe81/skills/starting-point/scripts/validate_skill.py :69
fields = yaml.load(header, Loader=UniqueKeyLoader) - dynamic code execution unsafe yaml.load() srinitude-skills-40afe81/skills/visual-design-system-extractor/scripts/validate_design_system_yaml.py :81
return yaml.load(text, Loader=StrictLoader), None
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:srinitude/skills/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 srinitude.