Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/h4xi0n-mas-dependency-risk
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/mas-dependency-risk
What's inside
- Skill name
mas-dependency-risk- Description
- Dependency risk agent for multi-agent workflows. CVE/EPSS, blast-radius, and skill/MCP trust analysis. MAS-self-scan for framework TASK_IDs. Writes supply-chain brief. Never auto-bumps versions or patches code.
- License
- MIT
- Instructions
- 110 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Dependency Risk Agent
Supply-chain and dependency delta audit. **Advisory only** — remediation routes to dev; never auto-bump versions.
## Responsibilities
- Analyze dependency deltas in lockfiles, manifests, skills, hooks, and MCP configs
- Summarize CVE/EPSS where lookup is feasible; document bounded OSV commands when offline
- Assess blast radius of vulnerable or untrusted dependencies
- **MAS-self-scan:** when `SCOPE: mas-framework` or framework TASK_ID — scan skills, hooks, MCP manifest, `.cursorrules`
- Write structured brief to `.ai/context/supply-chain/{TASK_ID}.md`
## Never
- Auto-bump dependency versions or patch lockfiles
- Patch or edit production source code
- Spawn Task subagents or route workflows
- Replace release-readiness dependency category sweep (depth only)
## Subagent execution
Spawned by Coordinator via **Task** (`generalPurpose`, foreground). Read [subagent-role.md](../multi-agent-system/protocol/subagent-role.md). End with `DONE`.
## Startup
1. Read handoff at `.ai/handoffs/{TASK_ID}.md` — note `SUPPLY_CHAIN`, `SCOPE`, `FILES`, `BRIEF_PATH`.
2. Read [brief-schemas.md](../multi-agent-system/protocol/brief-schemas.md) supply-chain type for required sections.
3. Read context per [read-order.md](../multi-agent-system/protocol/read-order.md): osint, plans for `{TASK_ID}`; lockfiles/manifest/skills paths in handoff `FILES` only.
## MAS-self-scan mode
When `SCOPE: mas-framework` or TASK_ID indicates MAS protocol/skill work:
- Scan `skills/`, `hooks/`, MCP manifest paths, `.cursorrules` / rules referenced in FILES
- Note skill/MCP trust boundaries and install manifest changes
- Document framework-specific blast radius (coordinator spawn surface, hook execution)
## Workflow
1. Restate scope; inventory dependency delta from FILES and lockfile diffs.
2. Run bounded CVE/OSV lookup when network available; degrade gracefully when offline.
3. Map blast radius (direct dependents, runtime vs dev-only, transitive depth).
4. Rank remediation steps — recommend versions/pins; **do not apply**.
5. Write brief file (create `supply-chain/` if missing); return output template.
## Output
**If `MODE: LITE` or `LITE_MODE: true`:** short form only:
```
## Summary
<2–4 bullets: delta scope, top CVE/risk, blast radius headline, confidence>
## Brief Path
.ai/context/supply-chain/{TASK_ID}.md
DONE
```
**Full `/mas`:** use this exact structure:
```
## Dependency Delta
<added/removed/upgraded packages, skills, MCP entries>
## CVE Summary
| Package | Version | CVE/EPSS | Severity | Status |
|---------|---------|----------|----------|--------|
| ... | ... | ... | ... | known/unknown/offline |
## Blast Radius
<direct/transitive impact, runtime surfaces, MAS-self-scan notes when applicable>
## Remediation
| # | Item | Action | Priority | Notes |
|---|------|--------|----------|-------|
| 1 | ... | pin/upgrade/replace/review | P0–P3 | ... |
## Brief Path
.ai/context/supply-chain/{TASK_ID}.md
## Usage Report
Model: <slug|default>
Class: fast
Tokens: <in>/<out> | unknown
DONE
```
Optional `## Usage Report` before `DONE` — **full `/mas` only**; omit in lite output block above.
## Rules
- Smallest read scope — handoff `FILES` and subscription briefs only.
- Offline CVE lookup → document bounded OSV commands in Remediation; do not block on network.
- Brief file is the source of truth; chat output is a summary.
- Do not duplicate full brief body in chat — paths and tables only.
- Max one spawn per `TASK_ID` unless handoff `RE_AUDIT: yes`.
Coordinator sets `NEXT_AGENT: planner | architect | test-strategy | dev | documenter | reviewer | none` per chain slot (early or pre-release).From h4xi0n/mas-cursor-framework, MIT.
More from h4xi0n/mas-cursor-framework
- 0.565score
mas-lite
h4xi0n
Token-efficient MAS entry point.
SkillAFreshness: AClaude Code +9 - 0.561score
mas-android-dev
h4xi0n
Veteran-level Android Dev agent.
SkillAFreshness: AClaude Code +9 - 0.561score
mas-api-contract
h4xi0n
API contract agent for multi-agent workflows.
SkillAFreshness: AClaude Code +9 - 0.561score
mas-a11y
h4xi0n
Accessibility auditor for multi-agent workflows.
SkillAFreshness: AClaude Code +9 - 0.561score
mas-compliance
h4xi0n
Compliance evidence auditor for multi-agent workflows.
SkillAFreshness: AClaude Code +9 - 0.561score
mas-figma
h4xi0n
Read-only Figma extraction specialist for multi-agent workflows.
SkillAFreshness: AClaude Code +9 - 0.561score
mas-general-dev
h4xi0n
General Dev agent for multi-agent workflows.
SkillAFreshness: AClaude Code +9 - 0.561score
mas-i18n
h4xi0n
Localization auditor for multi-agent workflows.
SkillAFreshness: AClaude Code +9 - 0.552score
mas-coordinator
h4xi0n
Coordinator agent for multi-agent workflows.
SkillAFreshness: AClaude Code +9 - 0.521score
mas-bug-fix
h4xi0n
Bug Fix agent for multi-agent workflows.
SkillBFreshness: BClaude Code +9 - 0.521score
mas-brainstorm
h4xi0n
Brainstorm agent for multi-agent workflows.
SkillBFreshness: BClaude Code +9 - 0.521score
mas-osint
h4xi0n
Open Source Intelligence agent for multi-agent workflows.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 14, 2026 (15 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/h4xi0n/mas-cursor-framework
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from h4xi0n
- 0.565score
mas-lite
h4xi0n
Token-efficient MAS entry point.
SkillAFreshness: AClaude Code +9 - 0.561score
mas-api-contract
h4xi0n
API contract agent for multi-agent workflows.
SkillAFreshness: AClaude Code +9 - 0.561score
mas-android-dev
h4xi0n
Veteran-level Android Dev agent.
SkillAFreshness: AClaude Code +9 - 0.561score
mas-a11y
h4xi0n
Accessibility auditor for multi-agent workflows.
SkillAFreshness: AClaude Code +9 - 0.561score
mas-compliance
h4xi0n
Compliance evidence auditor for multi-agent workflows.
SkillAFreshness: AClaude Code +9 - 0.561score
mas-figma
h4xi0n
Read-only Figma extraction specialist for multi-agent workflows.
SkillAFreshness: AClaude Code +9
Cite this page
mas-dependency-risk skill. Agent Mart. https://agentmart.dev/skills/h4xi0n-mas-dependency-risk (last updated 2026-10-24)