ITIL Ops
v1.0.0ITIL-aligned incident, problem, and change management for AI agents. Use when: detecting service crashes, analyzing recurring failures, tracking incidents to...
⭐ 0· 77·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name/description (ITIL-style incident/problem/change mgmt for agents) match the shipped instructions and script: the script reads journalctl, cron job state, agent memory, checks local health endpoints, classifies severities, and records state. The resources accessed (user journals, agent memory, coordination tasks) are expected for on-host monitoring of agent services.
Instruction Scope
The SKILL.md and scripts focus on detection, classification, ticket creation, and state storage. The script reads many local files and agent memory directories ($HOME/.skcapstone, $HOME/.openclaw, coordination tasks), which is appropriate for this purpose, but you should notice it has write actions (it saves itil-state.json and may create coordination tasks). The documentation mentions agents can "detect AND fix many incidents autonomously" (and "auto-remediate" in places) but the visible script primarily detects and records; if you rely on automatic remediation behavior, confirm whether additional code (not present in the provided files) performs changes.
Install Mechanism
No install spec is provided (instruction-only plus a shipped script). This minimizes supply-chain risk — nothing is downloaded or installed automatically by the skill. The included Bash script is run locally and will be written to disk when the skill is installed, which is expected for an ops helper.
Credentials
The skill requests no credentials or special environment variables, which fits its local-monitoring role. However it reads potentially sensitive local data: journal logs, agent memory JSON files, coordination task files, and local health endpoints. These accesses are reasonable for an on-host monitoring tool but mean the skill will see any secrets present in those stores — review what your agent stores in its memory and coordination paths before enabling.
Persistence & Privilege
The skill is not always-enabled and does not request system-wide configuration changes. It writes state to its own agent memory path and logs to an agent-local log file, which is expected. It does not request elevated credentials or alter other skills' configs in the provided code.
Assessment
This skill appears to do what it says: local incident detection, classification, and ticketing for an agent environment. Before installing, review the script (scripts/itil-review.sh) line-by-line and confirm you are comfortable with it reading your agent's memory and coordination directories and writing its state file (itil-state.json). If you have sensitive data in agent memory or task files, consider restricting file permissions or running the script with a least-privilege account. Also confirm whether any additional code (not included here) performs automatic remediation — the shipped script mainly detects and records issues, while the docs reference "auto-remediate" and autonomous fixes; if you need or want automatic changes, explicitly audit that logic and limit what can be changed without human approval.Like a lobster shell, security has layers — review code before you run it.
changevk97ehdw6gdy7kzp95nym9gcb5h83ce7cdevopsvk97ehdw6gdy7kzp95nym9gcb5h83ce7cincidentvk97ehdw6gdy7kzp95nym9gcb5h83ce7citilvk97ehdw6gdy7kzp95nym9gcb5h83ce7clatestvk97ehdw6gdy7kzp95nym9gcb5h83ce7cmonitoringvk97ehdw6gdy7kzp95nym9gcb5h83ce7copsvk97ehdw6gdy7kzp95nym9gcb5h83ce7cproblemvk97ehdw6gdy7kzp95nym9gcb5h83ce7csovereignvk97ehdw6gdy7kzp95nym9gcb5h83ce7csrevk97ehdw6gdy7kzp95nym9gcb5h83ce7c
License
MIT-0
Free to use, modify, and redistribute. No attribution required.