DC devops-agent
Your on-call DevOps assistant — one-click deploy, monitoring setup, scheduled backups, and fault diagnosis. Safety-first design with confirmation prompts, dry-run mode, snapshot rollback, and audit logging. (中文) 一键部署、监控搭建、定时备份、故障诊断，安全公约贯穿全局。
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.
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 22
-
high Dangerous commands
cmd-persistencescripts/backup-generator.sh:469Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null | grep -v "$SCRIPT_PATH"; echo "$SCHEDULE $SCRIPT_PATH >> ${LOG_FILE} 2>&1") | crontab -
Medium and low: 21
-
medium Exfiltration
net-credential-usescripts/backup-generator.sh:371Credential used in a network call (verify the destination is the intended service)curl -s -X POST "https://api.telegram.org/bot${BOT_TOKEN}/sendMessage" \ -
medium Dangerous commands
cmd-pipe-to-shellscripts/preflight-check.sh:124Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)docker) echo "curl -fsSL https://get.docker.com | sh" ;;
code literal -
medium Dangerous commands
cmd-privilegescripts/rollback.sh:253Privilege escalation / world-writable permissionsrun_cmd sudo cp "${SNAPSHOT_DIR}/nginx_config" "$nginx_conf" -
medium Dangerous commands
cmd-privilegescripts/rollback.sh:256Privilege escalation / world-writable permissionsrun_cmd sudo rm -f "$nginx_conf"
-
medium Dangerous commands
cmd-privilegescripts/rollback.sh:257Privilege escalation / world-writable permissionsrun_cmd sudo rm -f "/etc/nginx/sites-enabled/$site_name"
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash Read Write Edit Glob Grep Agent
-
medium Dangerous commands
cmd-persistenceSKILL.md:650Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)(crontab -l 2>/dev/null | grep -v "$BACKUP_SCRIPT"; echo "$CRON_SCHEDULE $BACKUP_SCRIPT") | crontab -
security skill -
low Dangerous commands
cmd-background-processreferences/systemd-templates.md:376Starts a background / autostarted process (documentation of a security skill)sudo systemctl enable {{APP_NAME}}security skill -
low Exfiltration
exfil-webhook-urlscripts/backup-generator.sh:371Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)curl -s -X POST "https://api.telegram.org/bot${BOT_TOKEN}/sendMessage" \placeholder -
low Dangerous commands
cmd-cron-mentionscripts/backup-generator.sh:469Mentions editing / listing crontab(crontab -l 2>/dev/null | grep -v "$SCRIPT_PATH"; echo "$SCHEDULE $SCRIPT_PATH >> ${LOG_FILE} 2>&1") | crontab - -
low Dangerous commands
cmd-background-processSKILL.md:226Starts a background / autostarted process (documentation of a security skill)sudo systemctl enable <app-name>
security skill -
low Dangerous commands
cmd-privilegeSKILL.md:322Privilege escalation / world-writable permissions (documentation of a security skill)sudo mv prometheus-*/prometheus /usr/local/bin/
security skill -
low Dangerous commands
cmd-privilegeSKILL.md:323Privilege escalation / world-writable permissions (documentation of a security skill)sudo mv prometheus-*/promtool /usr/local/bin/
security skill -
low Dangerous commands
cmd-privilegeSKILL.md:378Privilege escalation / world-writable permissions (documentation of a security skill)sudo mv node_exporter-*/node_exporter /usr/local/bin/
security skill -
low Dangerous commands
cmd-privilegeSKILL.md:412Privilege escalation / world-writable permissions (documentation of a security skill)echo "deb https://apt.grafana.com stable main" | sudo tee /etc/apt/sources.list.d/grafana.list
security skill -
low Dangerous commands
cmd-background-processSKILL.md:416Starts a background / autostarted process (documentation of a security skill)sudo systemctl enable grafana-server
security skill -
low Exfiltration
net-credential-useSKILL.md:430Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)curl -X POST -u "admin:${GRAFANA_ADMIN_PASS}" http://loca…000/api/datasources \security skill -
low Exfiltration
net-credential-useSKILL.md:441Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)curl -X POST -u "admin:${GRAFANA_ADMIN_PASS}" http://loca…000/api/dashboards/db \security skill -
low Exfiltration
exfil-webhook-urlSKILL.md:621Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)# curl -s -X POST "https://api.telegram.org/bot<TOKEN>/sendMessage" \
placeholder -
low Dangerous commands
cmd-privilegeSKILL.md:646Privilege escalation / world-writable permissions (documentation of a security skill)sudo cp generated_backup.sh "$BACKUP_SCRIPT"
security skill -
low Dangerous commands
cmd-cron-mentionSKILL.md:650Mentions editing / listing crontab (documentation of a security skill)(crontab -l 2>/dev/null | grep -v "$BACKUP_SCRIPT"; echo "$CRON_SCHEDULE $BACKUP_SCRIPT") | crontab -
security skill
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5112 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "user_invocable"
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
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 70Execution cost. Instruction body is 5112 tokens
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 35 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- low 10 top-level sections: this looks like several domains in one skill
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
- -2localhost URLs: will not work for another user
- +2Single-language instructions
- +3Description length 241: enough signal without eating the budget
- +4Structure: 52 headings
- +3Step-by-step instructions: 35 items
- +4Has examples (48 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 3 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.