Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add allsmog/vuln-scout --skill cross-componentgit clone --depth 1 https://github.com/allsmog/vuln-scoutWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/allsmog/vuln-scout/cross-component)<a href="https://agentmods.dev/skills/allsmog/vuln-scout/cross-component"><img src="https://agentmods.dev/badge/skills/allsmog/vuln-scout/cross-component/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/allsmog/vuln-scout/cross-component"><img src="https://agentmods.dev/badge/skills/allsmog/vuln-scout/cross-component.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00062 | $0.01565 |
| Opus 5 | $0.00031 | $0.00783 |
| Sonnet 5 | $0.00012 | $0.00313 |
| Haiku 4.5 | $0.00006 | $0.00156 |
Grade A, and why
cross-component scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-Component Security Analysis
Analyze how components interact and identify vulnerabilities that span service boundaries.
Why Cross-Component Analysis Matters
Single-component analysis misses:
- SSRF in frontend reaching internal backend
- Auth bypass when backend trusts frontend headers
- Data leakage through shared databases
- Privilege escalation via service-to-service calls
Step 1: Map the Architecture
Find Orchestration Configs
# Docker Compose
find . -name "docker-compose*.yml" -o -name "docker-compose*.yaml"
# Supervisord
find . -name "supervisord.conf" -o -name "supervisor*.conf"
# Kubernetes
find . -name "*.k8s.yaml" -o -name "deployment*.yaml" -o -name "service*.yaml"
# PM2
find . -name "ecosystem.config.js" -o -name "pm2*.json"
Extract Service Topology
# From docker-compose: services, ports, networks
grep -E "^\s+\w+:|ports:|expose:|depends_on:|networks:" docker-compose.yml
# From supervisord: programs and commands
grep -E "^\[program:|command=" supervisord.conf
# Internal-only services (not exposed externally)
grep -E "127\.0\.0\.1:|localhost:" docker-compose.yml supervisord.conf
Generate Service Map
## Service Topology
| Service | Port | Exposed | Language | Entry Points |
|---------|------|---------|----------|--------------|
| frontend | 1337 | ✅ External | Next.js | / |
| backend | 3000 | ❌ Internal | Flask | /api/* |
| redis | 6379 | ❌ Internal | - | - |
## Network Diagram
Internet → [1337] Next.js → [3000] Flask → [6379] Redis ↓ (Host header SSRF possible)
Step 2: Identify Trust Boundaries
Frontend → Backend Trust
# Does backend trust frontend headers?
grep -rn "X-User-ID\|X-Auth\|X-Forwarded\|X-Real-IP" --include="*.py" --include="*.go"
# Does backend skip auth for internal requests?
grep -rn "localhost\|127\.0\.0\.1\|internal" --include="*.py" --include="*.go" | grep -i "auth\|skip\|bypass"
Service-to-Service Auth
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 228 lines · 62 tokens per session scan A 876c3b816935
cross-component is a skill published in the GitHub repository allsmog/vuln-scout (24 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 1,565 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sast-config
Reviews and tunes SAST tool configurations against OWASP ASVS 4.0.3 and CWE Top 25. Auto-invoked when reviewing Semgrep rules, CodeQL queries, SAST CI integration, or false positive triage workflows. Produces a SAST maturity assessment covering rule authoring, severity tuning, custom rule development, and CI…
sast-semgrep
Static application security testing (SAST) using Semgrep for vulnerability detection, security code review, and secure coding guidance with OWASP and CWE framework mapping. Use when: (1) Scanning code for security vulnerabilities across multiple languages, (2) Performing security code reviews with pattern-based…
sast-semgrep
Static application security testing (SAST) using Semgrep for vulnerability detection, security code review, and secure coding guidance with OWASP and CWE framework mapping. Use when: (1) Scanning code for security vulnerabilities across multiple languages, (2) Performing security code reviews with pattern-based…
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
cloudflare-email-routing
Cloudflare Email Routing for receiving/sending emails via Workers. Use for email workers, forwarding, allowlists, or encountering Email Trigger errors, worker call failures, SPF issues.
bun-http-server
Use when building HTTP servers with Bun.serve, handling requests/responses, implementing routing, creating REST APIs, or configuring fetch handlers.