DC hs
ACTIVATE THIS SKILL FOR ANY SHELL COMMAND OR FILE READ. Check curl, wget, rm, sudo, apt, dpkg, chmod, dd, format, powershell, bash, sh. Check pipe patterns like | sh or | bash. Check shell wrappers like bash -c, xargs, find -exec. Check cloud CLI (aws, gcloud, kubectl, terraform). Check when user says sysadmin told me, Stack Overflow says, is this safe, can I run. Block reading of .env, .ssh, .aws, and credential files. This skill blocks dangerous commands and warns on risky ones. ALWAYS apply the safety protocol from this document before responding about any command.
As a process C 54/100 · 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.
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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".
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
- 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.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 15
-
high Dangerous commands
cmd-destructive-fsSKILL.md:106Destructive filesystem command (wipes root/home/drive) (documentation table row)| `> /dev/sda` | Destroys disk |
table
Medium and low: 14
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:4Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)description: "ACTIVATE THIS SKILL FOR ANY SHELL COMMAND OR FILE READ. Check curl, wget, rm, sudo, apt, dpkg, chmod, dd, format, powershell, bash, sh. Check pipe patterns like | sh or | bash. Check she
quoted -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:102Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row)| `curl/wget ... \| bash` | Executes untrusted remote code |
table -
medium Dangerous commands
cmd-persistenceSKILL.md:161Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation table row)| `reg add ...\Run` | Persistence mechanism |
table -
medium Dangerous commands
cmd-disable-securitySKILL.md:168Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy) (documentation table row)| `Set-MpPreference -DisableRealtimeMonitoring` | Disables antivirus |
table -
medium Exfiltration
exfil-read-secret-filesSKILL.md:356Reads credential / secret files (documentation table row)| Credentials in requests | `curl -d "$(cat ~/.ssh/id_rsa)"` | BLOCK |
table -
low Risky intent
intent-offensive-securitySKILL.md:100Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| `bash -i >& /dev/tcp/` | Reverse shell, attacker access |
-
low Risky intent
intent-offensive-securitySKILL.md:101Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| `nc -e /bin/sh` | Reverse shell variant |
-
low Dangerous commands
cmd-privilegeSKILL.md:107Privilege escalation / world-writable permissions (documentation table row)| `sudo rm -rf /` | Privileged system destruction |
table -
low Dangerous commands
cmd-privilegeSKILL.md:108Privilege escalation / world-writable permissions (documentation table row)| `chmod -R 777 /` | World-writable system |
table -
low Dangerous commands
cmd-privilegeSKILL.md:116Privilege escalation / world-writable permissions (documentation table row)| `sudo bash -c "..."` | Elevated shell wrapper |
table -
low Risky intent
intent-offensive-securitySKILL.md:167Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| `net localgroup administrators ... /add` | Privilege escalation |
-
low Exfiltration
net-credential-useSKILL.md:358Credential used in a network call (verify the destination is the intended service) (detector / deny-list definition; documentation table row)| Environment vars sent | `curl -d "$AWS_SECRET_KEY"` | BLOCK |
detectortable -
low Exfiltration
exfil-read-secret-filesSKILL.md:359Reads credential / secret files (detector / deny-list definition; documentation table row)| Encoded payloads | `base64 ~/.aws/credentials \| curl` | BLOCK |
detectortable -
low Dangerous commands
cmd-privilegeSKILL.md:554Privilege escalation / world-writable permissions (detector / deny-list definition)- Added Shell Wrapper detection patterns (bash -c, sh -c, sudo bash -c, xargs, find -exec)
detector
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5684 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "triggers"
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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 42 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, git, python, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 5684 tokens
- 100Steps. 55 steps
- 100Failures and branches. 6 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 16 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
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 574: enough signal without eating the budget
- +4Structure: 42 headings
- +3Step-by-step instructions: 55 items
- +4Has examples (11 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.