SKILLEMALL.ai
GitHub ↗ RU Sign in

FC dcg

Destructive Command Guard - High-performance Rust hook for Claude Code that blocks dangerous commands before execution. SIMD-accelerated, modular pack system, whitelist-first architecture. Essential safety layer for agent workflows.

Blockedguard blocked the skill: signs of malicious behaviour
Dicklesworthstone/destructive_command_guard Agent Skills author: Dicklesworthstone NOASSERTION 80 files body ≈ 3 774 tokens Open the sourcegithub.com↗ analyzed 30 h ago

Destructive Command Guard - High-performance Rust hook for Claude Code that blocks dangerous commands before execution.

As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

ProcedureDockerKubernetesPostgreSQLMySQLSoftware developmenttype 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
F
27/100
safety, quality, tests
Safety 60%
0
Quality 40%
68
Run on models
none yet
Process rating
C
52/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Consistency w 8
40
the three weakest of ten parameters · all ten
Guard blocked this skill: critical findings below. Do not install it until the author fixes them.

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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. Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
  2. 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 · 30

  • critical Dangerous commands cmd-destructive-fs benches/heredoc_perf.rs:41
    Destructive filesystem command (wipes root/home/drive)
    rm -rf /
  • critical Dangerous commands cmd-destructive-fs benches/heredoc_perf.rs:88
    Destructive filesystem command (wipes root/home/drive)
    rm -rf /
Medium and low: 28
  • medium Dangerous commands cmd-pipe-to-shell .github/workflows/dcg-scan.yml:71
    Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)
    curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --profile minimal
    security skill
  • medium Exfiltration exfil-read-secret-files CHANGELOG.md:1077
    Reads credential / secret files (documentation of a security skill)
    tee ~/.SSH/id_rsa              cp evil ~/.SSH/id_rsa
    security skill
  • low Dangerous commands cmd-pipe-to-shell-known-host .beads/README.md:64
    Pipe-to-shell installer from a well-known host (still executes remote code) (documentation of a security skill)
    curl -sSL https://raw.githubusercontent.com/steveyegge/beads/main/scripts/install.sh | bash
    security skill
  • low Concealment en-hide-from-user .skill-loop-progress.md:64
    Instruction to hide actions from the user (negated — the text forbids it)
    | 1 | Correct project-extension anchoring to OMP's cwd-only discovery; prove nested Git cwd does not silently install an unloaded file. | complete | `72e6c42`; 7 Rust + 10 targeted Bats green |
    negated
  • low Risky intent intent-offensive-security .skill-loop-progress.md:367
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    behavior is passes 21/34; large-command and control-byte behavior is pass 31.
    detector
  • low Secrets in code secret-high-entropy-token .skill-loop-progress.md:1548
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    `PASS…-v2`, SHA-256
    quoted
  • low Dangerous commands cmd-destructive-fs-scoped CHANGELOG.md:1107
    Destructive command on a partition / current directory (normal in admin docs; verify the target) (documentation table row; documentation of a security skill)
    | `dd if=/dev/zero of=/dev/sda 2>>/var/log/dd.log` | DENY `dd-device` |
    tablesecurity skill
  • low Dangerous commands cmd-destructive-fs-scoped CHANGELOG.md:1111
    Destructive command on a partition / current directory (normal in admin docs; verify the target) (documentation table row; documentation of a security skill)
    | `wipefs -a /dev/sdb -o /tmp/wipe.bak` | DENY `wipefs` |
    tablesecurity skill
  • low Dangerous commands cmd-privilege CHANGELOG.md:1115
    Privilege escalation / world-writable permissions (documentation table row; documentation of a security skill)
    | `chmod -R 777 /etc --reference=/tmp/stat` | **allowed** |
    tablesecurity skill
  • low Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:197
    Pipe-to-shell installer from a well-known host (still executes remote code) (documentation of a security skill)
    curl -fsSL "https://raw.githubusercontent.com/Dicklesworthstone/destructive_command_guard/main/install.sh?$(date +%s)" | bash
    security skill
  • low Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:200
    Pipe-to-shell installer from a well-known host (still executes remote code) (documentation of a security skill)
    curl -fsSL "https://raw.githubusercontent.com/Dicklesworthstone/destructive_command_guard/main/install.sh?$(date +%s)" | bash -s -- --easy-mode
    security skill
  • low Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:203
    Pipe-to-shell installer from a well-known host (still executes remote code) (documentation of a security skill)
    curl -fsSL "https://raw.githubusercontent.com/Dicklesworthstone/destructive_command_guard/main/install.sh?$(date +%s)" | sudo bash -s -- --system
    security skill

A further 16 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 78. 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")

Process rating: all ten parameters 52/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Consistency. Frontmatter name (dcg) differs from the folder (destructive_command_guard)
  • 50When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash, web, git) that frontmatter does not declare
  • 100Steps. 31 steps
  • 100Execution cost. Instruction body is 3774 tokens
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 19 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (5 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

  • +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
  • -419 reference files, but SKILL.md never points to them: the model will not open them
  • +1No license
  • +2Single-language instructions
  • +3Description length 232: enough signal without eating the budget
  • +4Structure: 57 headings
  • +3Step-by-step instructions: 31 items
  • +4Has examples (13 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.