FC llm-shell-guard
(no description)
Not recommendedcritical or high security findings · low grade F
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Add a description to the frontmatter: without it the skill never triggers.
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 · 13
-
high Dangerous commands
cmd-destructive-fslinux_command_guard/rules/denylist.txt:1Destructive filesystem command (wipes root/home/drive) (documentation of a security skill)rm -rf /
security skill -
high Dangerous commands
cmd-destructive-fslinux_command_guard/rules/denylist.txt:2Destructive filesystem command (wipes root/home/drive) (documentation of a security skill)rm -rf /*
security skill -
high Dangerous commands
cmd-destructive-fslinux_command_guard/rules/denylist.txt:3Destructive filesystem command (wipes root/home/drive) (documentation of a security skill)rm -rf ~
security skill -
high Dangerous commands
cmd-destructive-fslinux_command_guard/rules/denylist.txt:4Destructive filesystem command (wipes root/home/drive) (documentation of a security skill)rm -rf $HOME
security skill -
high Dangerous commands
cmd-destructive-fslinux_command_guard/rules/denylist.txt:9Destructive filesystem command (wipes root/home/drive) (documentation of a security skill):(){ :|:& };:security skill
Medium and low: 8
-
medium Dangerous commands
cmd-destructive-fs-scopedlinux_command_guard/rules/denylist.txt:15Destructive command on a partition / current directory (normal in admin docs; verify the target) (documentation of a security skill)wipefs -a
security skill -
medium Dangerous commands
cmd-destructive-fs-scopedlinux_command_guard/rules/denylist.txt:16Destructive command on a partition / current directory (normal in admin docs; verify the target) (documentation of a security skill)shred /dev/
security skill -
medium Dangerous commands
cmd-pipe-to-shelllinux_command_guard/rules/denylist.txt:20Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)curl | sh
security skill -
medium Dangerous commands
cmd-pipe-to-shelllinux_command_guard/rules/denylist.txt:21Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)curl | bash
security skill -
medium Dangerous commands
cmd-pipe-to-shelllinux_command_guard/rules/denylist.txt:22Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)wget -qO- | sh
security skill -
medium Dangerous commands
cmd-pipe-to-shelllinux_command_guard/rules/denylist.txt:23Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)wget -qO- | bash
security skill -
low Dangerous commands
cmd-background-processlinux_command_guard/checker.py:99Starts a background / autostarted process (string literal in code, not executed; documentation of a security skill)"setsid ",
code literalsecurity skill -
low Dangerous commands
cmd-pipe-to-shellREADME.md:96Downloads and executes remote code from an unrecognised host (pipe to shell) (negated — the text forbids it)- `curl http://example.com/x.sh | sh`
negated
Files scanned: 21. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
frontmatterSKILL.md: no YAML frontmatter block found - error
name-missingSKILL.md: frontmatter has no `name` - error
description-missingSKILL.md: no `description` — the skill can never trigger
Process rating: all ten parameters 51/100
- 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
- 30When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python, node) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 100Steps. 44 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 489 tokens
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)
- +3Description length 0: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 4 headings
- +3Step-by-step instructions: 44 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 0.
External checks
ClawHub: clean
This is a defensive local command-checking skill that matches its stated purpose and shows no evidence of hidden execution, data collection, persistence, or destructive behavior.
LLM: benign (high) · VirusTotal: · 29 May 2026