SKILLEMALL.ai
GitHub ↗ RU Sign in

BF agents-harden

Use when preparing your agent for production — IAM scoping, inbound auth (JWT, SigV4), secrets management, cold start optimization, session lifecycle, rate limiting, input validation, and quota guidance. Triggers on: "production checklist", "harden agent", "production ready", "secure agent", "inbound auth", "going live", "cold start optimization", "session lifecycle", "StopRuntimeSession", "quota", "throttling", "maxVms", "rate limit", "security audit of outbound API calls", "gateway target audit for production", "restrict who can call", "lock down endpoint", "only our app can call". Not for Cedar tool-restriction policies — use agents-connect. Not for quality measurement — use agents-optimize. Not for outbound credential storage or API key wiring — use agents-connect. Not for A2A agent-to-agent auth — use agents-build. Cold start observation and diagnosis (not optimization) routes to agents-debug.

ClawHub Agent Skills author: Amazon Web Services 1 file body ≈ 7 748 tokens Open the sourceclawhub.ai↗ analyzed 15 h ago

Use when preparing your agent for production — IAM scoping, inbound auth (JWT, SigV4), secrets management, cold start optimization, session lifecycle, rate…

As a process F 66/100 · Will not run — References files that are not bundled: references/limits.md, ../agents-build/references/integrate.md, ../agents-connect/SKILL.md

ProcedureAWSAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
85/100
safety, quality, tests
Safety 60%
95
Quality 40%
71
Run on models
none yet
Process rating
F
66/100
Will not run
References files that are not bundled: references/limits.md, ../agents-build/references/integrate.md, ../agents-connect/SKILL.md
Tools and files w 18
0
Running it twice w 4
30
Result and completion w 14
60
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 1

✓ No critical or high findings

Medium and low: 1
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Read Grep Glob Bash

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 7748 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/limits.md
  • warning missing-ref reference to a missing file: ../agents-build/references/integrate.md
  • warning missing-ref reference to a missing file: ../agents-connect/SKILL.md
  • warning missing-ref reference to a missing file: ../agents-build/references/vpc.md
  • warning missing-ref reference to a missing file: ../agents-debug/SKILL.md
  • warning missing-ref reference to a missing file: references/vpc.md

Process rating: all ten parameters 66/100

Will not run. References files that are not bundled: references/limits.md, ../agents-build/references/integrate.md, ../agents-connect/SKILL.md
  • 0Tools and files. 6 referenced file(s) missing: references/limits.md, ../agents-build/references/integrate.md, ../agents-connect/SKILL.md
  • 30Running it twice. 16 mutating operations with no state check
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 7748 tokens
  • 85Steps. 59 steps, 2 vague phrases
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • low 19 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +3Description length 911: 120–800 characters recommended
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 17 example trigger phrases
  • +4Description says when NOT to use the skill
  • +4Structure: 40 headings
  • +3Step-by-step instructions: 59 items
  • +3Output format is stated explicitly
  • +4Has examples (24 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.