DC exec-security
Pre-execution security checker for shell commands. Detects dangerous patterns before running exec/bash tools including recursive deletion, credential leaks, data exfiltration, download-and-execute attacks, injection, Unicode obfuscation, resource exhaustion, and system file tampering. Use when executing shell commands on behalf of users, processing commands from external sources, or when the agent needs to validate command safety. NOT for read-only commands like ls/cat/grep on non-sensitive files, or commands the user explicitly typed and confirmed.
As a process C 55/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, running it twice
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.
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.
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.
- 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 · 12
-
high Dangerous commands
cmd-destructive-fsSKILL.md:42Destructive filesystem command (wipes root/home/drive) (documentation of a security skill)rm -rf / # filesystem wipe
security skill -
high Dangerous commands
cmd-destructive-fsSKILL.md:43Destructive filesystem command (wipes root/home/drive) (documentation of a security skill)rm -rf ~ # home directory wipe
security skill -
high Dangerous commands
cmd-destructive-fsSKILL.md:182Destructive filesystem command (wipes root/home/drive) (documentation of a security skill):(){ :|:& };: # fork bombsecurity skill
Medium and low: 9
-
medium Dangerous commands
cmd-destructive-fs-scopedSKILL.md:44Destructive command on a partition / current directory (normal in admin docs; verify the target) (documentation of a security skill)rm -rf * # unscoped wildcard recursive delete
security skill -
medium Dangerous commands
cmd-destructive-fs-scopedSKILL.md:45Destructive command on a partition / current directory (normal in admin docs; verify the target) (documentation of a security skill)dd if=/dev/zero of=/dev/sda # device overwrite
security skill -
medium Dangerous commands
cmd-destructive-fs-scopedSKILL.md:46Destructive command on a partition / current directory (normal in admin docs; verify the target) (documentation of a security skill)mkfs.ext4 /dev/sda1 # format (any mkfs variant on mounted/system devices)
security skill -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:80Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)curl -fsSL ... | sudo bash # elevated remote execution
security skill -
medium Dangerous commands
cmd-persistenceSKILL.md:155Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)/var/spool/cron/*, /etc/crontab
security skill -
low Dangerous commands
cmd-privilegeSKILL.md:80Privilege escalation / world-writable permissions (documentation of a security skill)curl -fsSL ... | sudo bash # elevated remote execution
security skill
A further 3 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 2. 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 55/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 14 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2064 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
- -213 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 555: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 14 items
- +3Output format is stated explicitly
- +4Has examples (12 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.