SKILLEMALL.ai
GitHub ↗ RU Sign in

CC runtime-sentinel

Runtime security guardian for OpenClaw agents. Use this skill whenever the user mentions security, skill safety, prompt injection, malware, suspicious behavior, credential leaks, network monitoring, skill integrity, or the ClawHavoc attack. Also trigger for phrases like "is this skill safe", "audit my skills", "check for threats", "my agent is acting weird", "scan for malware", "protect my agent", or any concern about what installed skills are doing at runtime. runtime-sentinel provides five active defenses: skill integrity hashing, prompt injection detection, credential exposure auditing, network egress monitoring, and process anomaly detection. Free tier covers hashing and basic injection scanning. Premium features (continuous daemon, egress monitoring, process anomaly detection) are gated via x402 USDC micropayments on Base — no account or API key required.

LeoYeAI/openclaw-master-skills Agent Skills author: LeoYeAI MIT 19 files body ≈ 1 358 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Runtime security guardian for OpenClaw agents.

As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions

ProcedureAI and agentsInfrastructuretype 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
71/100
safety, quality, tests
Safety 60%
58
Quality 40%
91
Run on models
none yet
Process rating
C
59/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
50
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.

Risky intent 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 purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.

For the author

Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.

Concealment 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 tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.

For the author

Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".

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 · 22

    ✓ No critical or high findings

    Medium and low: 22
    • medium Risky intent intent-wallet-secrets README.md:65
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      - **`wallet/mnemonic.enc`** — 12-word recovery phrase, AES-256-GCM, separate Argon2id derivation
    • medium Risky intent intent-wallet-secrets README.md:67
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      Back up your recovery phrase with `sentinel wallet export`. Recovery on a new machine: `sentinel wallet recover`.
    • medium Concealment en-hide-from-user references/threat-model.md:102
      Instruction to hide actions from the user (documentation of a security skill)
      the agent to silently forward all email drafts to an attacker address.
      security skill
    • medium Risky intent intent-wallet-secrets references/x402-payment.md:73
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      **Security**: The wallet private key is stored encrypted at
    • medium Risky intent intent-wallet-secrets scripts/src/payment.rs:241
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      // Re-encrypt the mnemonic phrase for this machine
    • low Dangerous commands cmd-background-process README.md:40
      Starts a background / autostarted process (documentation of a security skill)
      disown
      security skill
    • low Dangerous commands cmd-privilege README.md:89
      Privilege escalation / world-writable permissions (documentation of a security skill)
      chmod +x sentinel && sudo mv sentinel /usr/local/bin/
      security skill
    • low Dangerous commands cmd-privilege README.md:93
      Privilege escalation / world-writable permissions (documentation of a security skill)
      chmod +x sentinel && sudo mv sentinel /usr/local/bin/
      security skill
    • low Dangerous commands cmd-privilege README.md:97
      Privilege escalation / world-writable permissions (documentation of a security skill)
      chmod +x sentinel && sudo mv sentinel /usr/local/bin/
      security skill
    • low Dangerous commands cmd-privilege README.md:101
      Privilege escalation / world-writable permissions (documentation of a security skill)
      chmod +x sentinel && sudo mv sentinel /usr/local/bin/
      security skill
    • low Secrets in code secret-high-entropy-token scripts/src/payment.rs:21
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      const TREASURY_ADDRESS: &str = "0x0E…305";
      quoted
    • low Secrets in code secret-high-entropy-token scripts/src/payment.rs:24
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      const USDC_BASE: &str = "0x83…913";
      quoted
    • low Risky intent intent-wallet-secrets scripts/src/payment.rs:154
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
      println!("⚠️  This will display your 12-word recovery phrase.");
      quoted
    • low Risky intent intent-wallet-secrets scripts/src/payment.rs:187
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
      println!("Recovery phrase (12 words — write these down, in order):");
      quoted
    • low Risky intent intent-wallet-secrets scripts/src/payment.rs:203
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
      println!("Enter your 12-word recovery phrase (words separated by spaces):");
      quoted
    • low Risky intent intent-wallet-secrets scripts/src/payment.rs:211
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)
      .map_err(|e| anyhow::anyhow!("Invalid recovery phrase: {}", e))?;
      detector
    • low Secrets in code secret-high-entropy-token scripts/src/payment.rs:651
      High-entropy token-like string (may be an id, hash or a credential)
      // USDC contract on Base: 0x83…913
    • low Secrets in code secret-high-entropy-token scripts/src/payment.rs:656
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "to": "0x83…913",
      quoted
    • low Dangerous commands cmd-background-process SKILL.md:126
      Starts a background / autostarted process (documentation of a security skill)
      #   disown
      security skill
    • low Risky intent intent-offensive-security SKILL.md:152
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      - **CRITICAL**: Active exfiltration attempt, reverse shell indicator, or
      detector

    A further 2 matches are quotations in this security skill's documentation and are not counted as findings.

    Files scanned: 19. 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 59/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 24 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1358 tokens
    • 100Running it twice. No mutating operations
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low The response is described with custom markup (3 tags): a typed call is more reliable

    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

    • +4Description does not say when NOT to use the skill (false activations)
    • +3Description length 872: 120–800 characters recommended
    • +3Output format is not stated: the model decides each time
    • +2Single-language instructions
    • +5Description quotes 6 example trigger phrases
    • +4Structure: 15 headings
    • +3Step-by-step instructions: 24 items
    • +4Has examples (6 code blocks)
    • +4Reference files are cited in the instructions (3 of 3)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.