security-posture

security-posture is a skill for Claude Code, Codex from AlgoChains/algochains-mcp-server. It costs 0 tokens per session (504 once invoked), scanned A, original, MIT.

A read-only security audit for an MCP server, checking twelve CoSAI threat categories and selected SAFE-MCP attack techniques. It reports which protections are covered, partial, or still open.

In plain words
What is it for?
Run it weekly or on demand to review the server’s security coverage and identify areas that need attention.
Why use it?
It provides a repeatable way to find security gaps in tool connections, credentials, signed requests, rate limits, and emergency controls.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Run it weekly or on demand to review the server’s security coverage and identify areas that need attention.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/algochains/algochains-mcp-server/security-posture
Install

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.

Any agent
npx skills add AlgoChains/algochains-mcp-server --skill security-posture
Clone the repo
git clone --depth 1 https://github.com/AlgoChains/algochains-mcp-server

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for security-posture

README.md
[![agentmods](https://agentmods.dev/badge/skills/algochains/algochains-mcp-server/security-posture/github.svg)](https://agentmods.dev/skills/algochains/algochains-mcp-server/security-posture)
Your own site
<a href="https://agentmods.dev/skills/algochains/algochains-mcp-server/security-posture"><img src="https://agentmods.dev/badge/skills/algochains/algochains-mcp-server/security-posture/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.

agentmods 80×15 button for security-posture

Your own site · 80×15
<a href="https://agentmods.dev/skills/algochains/algochains-mcp-server/security-posture"><img src="https://agentmods.dev/badge/skills/algochains/algochains-mcp-server/security-posture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 504 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00504
Opus 5.5 $0.00000 $0.00202
Sonnet 5.5 $0.00000 $0.00101
Haiku 4.5 $0.00000 $0.00050

Measured 2mo ago against content hash 6c9db63a5f32, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

security-posture 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 2mo 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.

algoclaw/skills/security-posture/SKILL.md · 57 lines

What it actually says

security-posture

Tier: 0 (safe, read-only)
Trigger: Weekly (Sunday 2 AM), on-demand
MCP Tool: run_algoclaw_skill("security-posture")

What It Does

Runs a systematic audit of the MCP server against CoSAI 12-category threats and SAFE-MCP 81 techniques. Returns a coverage report showing what's protected and what's still open.

Steps

  1. Check CoSAI 12 categories (hardcoded knowledge of current coverage)
  2. Check SAFE-MCP critical techniques: T001, T012, T034, T051, T067, T071, T078, T089, T094
  3. Call get_rate_limit_status() for all destructive tools
  4. Call check_all_broker_credentials() — verify no credentials exposed
  5. Check replay guard: verify_hmac_signature wired to all signed endpoints?
  6. Check that kill-switch has owner-ID gate
  7. Compute coverage score: covered/total × 100

Output Format

{
  "audit_date": "2026-04-08",
  "cosai_coverage": {
    "total_categories": 12,
    "covered": 7,
    "partial": 2,
    "open": 3,
    "score_pct": 58.3
  },
  "safe_mcp_coverage": {
    "T001_command_injection": "partial",
    "T012_fake_tool_invocation": "partial",
    "T034_path_traversal": "open",
    "T051_replay_attack": "covered",
    "T067_rate_limit_bypass": "covered",
    "T071_session_token_theft": "partial",
    "T078_tool_description_manipulation": "open",
    "T089_dos_resource_exhaustion": "open",
    "T094_injection_via_tool_output": "open"
  },
  "open_items": [
    "T034: Add path_validator() to file-writing tools",
    "T078: Hash tool descriptions at startup",
    "T089: Per-client total request budget",
    "T094: Sanitize Onyx output before agent context"
  ],
  "credential_check": "all_masked",
  "rate_limits_active": true,
  "replay_guard_active": true,
  "owner_gate_active": true
}
Changes

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.

  1. 2mo ago First seen · 57 lines · 0 tokens per session scan A 6c9db63a5f32

Subscribe to this mod's changes

security-posture is a skill published in the GitHub repository AlgoChains/algochains-mcp-server (1 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 504 tokens. 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 2026-08-31.

Related

security-posture compared with skills from other repositories

security-posture next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
security-postureAlgoChains/algochains-mcp-serverSkill11mo agoMITA0Claude Code, Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex