SKILLEMALL.ai
GitHub ↗ RU Sign in

BC tinman

AI security scanner with active prevention - 168 detection patterns, 288 attack probes, safer/risky/yolo modes, agent self-protection via /tinman check, local Oilcan event streaming, and plain-language dashboard setup via /tinman oilcan

modbender/skill-library-mcp Agent Skills author: modbender MIT 3 files body ≈ 2 329 tokens Open the sourcegithub.com↗ analyzed 2 d ago

AI security scanner with active prevention - 168 detection patterns, 288 attack probes, safer/risky/yolo modes, agent self-protection via /tinman check, local…

As a process C 54/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerAI and agentsData and analyticstype 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
80/100
safety, quality, tests
Safety 60%
87
Quality 40%
70
Run on models
none yet
Process rating
C
54/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
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. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 9

✓ No critical or high findings

Medium and low: 9
  • medium Exfiltration intent-browser-credential-store tinman_runner.py:533
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    "browser_data": ["Cookies", "Login Data", "Chrome", "Firefox", "Safari", "Brave"],
    quoted
  • low Risky intent intent-wallet-secrets tinman_runner.py:529
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    "seed phrase",
    quoted
  • low Risky intent intent-wallet-secrets tinman_runner.py:531
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    "recovery phrase",
    quoted
  • low Dangerous commands cmd-execpolicy-bypass tinman_runner.py:555
    Runs PowerShell with execution policy bypassed (string literal in code, not executed)
    "-executionpolicy bypass",
    code literal
  • low Dangerous commands cmd-background-process tinman_runner.py:589
    Starts a background / autostarted process (string literal in code, not executed)
    "systemctl enable",
    code literal
  • low Dangerous commands cmd-privilege tinman_runner.py:631
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    "privilege_escalation": ["sudo", "chmod 777", "chmod +x", "chown", "setuid"],
    code literal

A further 3 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • note frontmatter-key unknown frontmatter key "repository"
  • note frontmatter-key unknown frontmatter key "requires"
  • note frontmatter-key unknown frontmatter key "install"
  • note frontmatter-key unknown frontmatter key "permissions"

Process rating: all ten parameters 54/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (tinman) differs from the folder (agent-tinman)
  • 50Failures and branches. 0 branches, has a failure section
  • 100Tools and files. No external tools needed
  • 100Steps. 36 steps
  • 100Execution cost. Instruction body is 2329 tokens
  • 100Running it twice. Mutating operations check current state
  • 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
  • +2Single-language instructions
  • +3Description length 236: enough signal without eating the budget
  • +4Structure: 20 headings
  • +3Step-by-step instructions: 36 items
  • +4Has examples (16 code blocks)
  • +1License stated

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