FD it-operations
Manages IT infrastructure, monitoring, incident response, and service reliability. Provides frameworks for ITIL service management, observability strategies, automation, backup/recovery, capacity planning, and operational excellence practices.
Manages IT infrastructure, monitoring, incident response, and service reliability.
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
The same skill appears in 1 more place: RA-Skills
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.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 11
-
high Dangerous commands
cmd-disable-securityreference/infrastructure.md:384Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy)iptables -F
-
high Dangerous commands
cmd-destructive-fs-scopedreference/infrastructure.md:869Destructive command on a partition / current directory (normal in admin docs; verify the target)mkfs.ext4 /dev/data_vg/database_lv
-
high Dangerous commands
cmd-destructive-fs-scopedreference/infrastructure.md:870Destructive command on a partition / current directory (normal in admin docs; verify the target)mkfs.xfs /dev/data_vg/backups_lv
Medium and low: 8
-
medium Exfiltration
exfil-webhook-urlreference/monitoring.md:651Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)- api_url: 'https://hooks.slack.com/services/XXX'
quoted -
medium Exfiltration
exfil-webhook-urlreference/monitoring.md:672Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)- api_url: 'https://hooks.slack.com/services/YYY'
quoted -
low Risky intent
intent-offensive-securityreference/backup-recovery.md:430Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Anti-ransomware
-
low Risky intent
intent-offensive-securityreference/backup-recovery.md:545Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Catastrophic system failure (ransomware, data corruption)
-
low Dangerous commands
cmd-background-processreference/infrastructure.md:95Starts a background / autostarted processsystemctl enable chrony
-
low Dangerous commands
cmd-background-processreference/infrastructure.md:131Starts a background / autostarted processsystemctl enable node_exporter
-
low Dangerous commands
cmd-background-processreference/infrastructure.md:161Starts a background / autostarted processsystemctl enable fail2ban
-
low Dangerous commands
cmd-background-processreference/infrastructure.md:931Starts a background / autostarted processsystemctl enable libvirtd
Files scanned: 7. 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")
Process rating: all ten parameters 43/100
- 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 69 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3665 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 243: enough signal without eating the budget
- +4Structure: 32 headings
- +3Step-by-step instructions: 69 items
- +4Has examples (10 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.