SKILLEMALL.ai
GitHub ↗ RU Sign in

CF opnsense-admin

Manage OPNsense firewall, DNS, IDS/IPS, and network configuration via API and SSH. Use when administering OPNsense firewall, configuring Suricata IDS/IPS, managing Unbound DNS, creating firewall rules, backing up configurations, monitoring traffic, or troubleshooting network issues. Supports both API-based automation and SSH command execution for OPNsense 26.1+.

modbender/skill-library-mcp Agent Skills author: modbender MIT 6 files · 3 scripts body ≈ 1 823 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Manage OPNsense firewall, DNS, IDS/IPS, and network configuration via API and SSH.

As a process F 45/100 · Will not run — References files that are not bundled: references/api-guide.md, references/firewall-rules.md, references/suricata-ips.md

IntegrationInfrastructureWriting and documentstype 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
C
72/100
safety, quality, tests
Safety 60%
70
Quality 40%
75
Run on models
none yet
Process rating
F
45/100
Will not run
References files that are not bundled: references/api-guide.md, references/firewall-rules.md, references/suricata-ips.md
Tools and files w 18
0
Result and completion w 14
0
Progress reporting w 2
0
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. 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 · 6

✓ No critical or high findings

Medium and low: 6
  • medium Exfiltration net-credential-use scripts/backup-config.sh:114
    Credential used in a network call (verify the destination is the intended service)
    curl -s $INSECURE_FLAG -u "${OPNSENSE_KEY}:${OPNSENSE_SECRET}" \
  • medium Exfiltration net-credential-use scripts/backup-config.sh:119
    Credential used in a network call (verify the destination is the intended service)
    curl -s $INSECURE_FLAG -u "${OPNSENSE_KEY}:${OPNSENSE_SECRET}" \
  • medium Exfiltration net-credential-use scripts/opnsense-api.sh:99
    Credential used in a network call (verify the destination is the intended service)
    curl -s $INSECURE_FLAG -u "${OPNSENSE_KEY}:${OPNSENSE_SECRET}" \
  • medium Exfiltration net-credential-use scripts/opnsense-api.sh:101
    Credential used in a network call (verify the destination is the intended service)
    "$url" | jq . 2>/dev/null || curl -s $INSECURE_FLAG -u "${OPNSENSE_KEY}:${OPNSENSE_SECRET}" "$url"
  • medium Exfiltration net-credential-use scripts/opnsense-api.sh:103
    Credential used in a network call (verify the destination is the intended service)
    curl -s $INSECURE_FLAG -u "${OPNSENSE_KEY}:${OPNSENSE_SECRET}" \
  • medium Exfiltration net-credential-use scripts/opnsense-api.sh:108
    Credential used in a network call (verify the destination is the intended service)
    "$url" | jq . 2>/dev/null || curl -s $INSECURE_FLAG -u "${OPNSENSE_KEY}:${OPNSENSE_SECRET}" -X POST -d "$data" "$url"

Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/api-guide.md
  • warning missing-ref reference to a missing file: references/firewall-rules.md
  • warning missing-ref reference to a missing file: references/suricata-ips.md
  • warning missing-ref reference to a missing file: references/unbound-dns.md
  • warning missing-ref reference to a missing file: references/quick-ref.md

Process rating: all ten parameters 45/100

Will not run. References files that are not bundled: references/api-guide.md, references/firewall-rules.md, references/suricata-ips.md
  • 0Tools and files. 5 referenced file(s) missing: references/api-guide.md, references/firewall-rules.md, references/suricata-ips.md
  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 4 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 37 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1823 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 11 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

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 364: enough signal without eating the budget
  • +4Structure: 26 headings
  • +3Step-by-step instructions: 37 items
  • +4Has examples (9 code blocks)
  • +3All 3 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.