SKILLEMALL.ai
GitHub ↗ RU Sign in

CC oma-security

Scan application source, agent skills, and MCP components; run penetration tests against scoped web test deployments, validate findings, and configure scan gates. Use oma-qa for broad quality reviews and domain skills for remediation.

first-fluke/oh-my-agent Agent Skills author: first-fluke 31 files body ≈ 3 807 tokens Open the sourcegithub.com↗ analyzed 15 h ago

Scan application source, agent skills, and MCP components; run penetration tests against scoped web test deployments, validate findings, and configure scan…

As a process C 61/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice

AnalyzerCloudflareAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
C
88/100
safety, quality, tests
Safety 60%
91
Quality 40%
84
Run on models
none yet
Process rating
C
61/100
Has gaps
Result and completion w 14
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

The same skill appears in 2 more places: oh-my-agent, oh-my-agent

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

    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 · 5

    ✓ No critical or high findings

    Medium and low: 5
    • medium Exfiltration intent-browser-credential-store SKILL.md:139
      Accesses a browser credential / cookie store (documentation of a security skill)
      Keep raw originals unchanged and access-controlled; shared/normalized copies omit passwords, keys, cookies, authorization headers, and private user data.
      security skill
    • low Risky intent intent-offensive-security resources/artex.md:3
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      Load for an explicit ARTEX request or a concrete `web_runtime`/`pentest` target.
      detector
    • low Risky intent intent-offensive-security SKILL.md:23
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Run a bounded runtime penetration test against a concrete authorized test deployment.
    • low Risky intent intent-offensive-security SKILL.md:36
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      - `intent`: `setup | scan | diff | pentest | triage | validate | ci | troubleshoot`.
      detector
    • low Risky intent intent-offensive-security SKILL.md:78
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition; documentation table row)
      | Web test deployment (`web_runtime`, `pentest`) | ARTEX | Independent runtime replay of candidates |
      detectortable

    Files scanned: 31. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 61/100

    • 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. 25 mutating operations with no state check
    • 50Failures and branches. 0 branches, has a failure section
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 85Steps. 66 steps, 1 vague phrases
    • 100Tools and files. No external tools needed
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3807 tokens
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    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 234: enough signal without eating the budget
    • +4Structure: 20 headings
    • +3Step-by-step instructions: 66 items
    • +4Has examples (1 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.