CF cicd-workflow
CI/CD workflow skill for Java + Vue projects. Supports GitLab CI and Jenkins pipelines with code linting, unit testing, build packaging, Docker image building, Kubernetes deployment, and notification feedback. Use when: (1) Setting up CI/CD pipelines for Java/Vue projects, (2) Configuring GitLab CI or Jenkins workflows, (3) Building Docker images and deploying to Kubernetes, (4) Implementing automated code quality checks and testing, (5) Setting up deployment notifications.
As a process F 53/100 · Will not run — References files that are not bundled: assets/gitlab-ci.yml.txt
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 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 text references files that are not there: add them or drop the references.
- 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 · 6
-
high Exfiltration
exfil-read-secret-filesassets/gitlab-ci.yml:207Reads credential / secret files- echo "$KUBE_CONFIG" | base64 -d > ~/.kube/config
Medium and low: 5
-
medium Exfiltration
exfil-read-secret-filesscripts/generate-setup-guide.py:234Reads credential / secret files (quoted — discussed, not commanded)cat ~/.kube/config | base64
quoted -
low Dangerous commands
cmd-privilegescripts/generate-setup-guide.py:147Privilege escalation / world-writable permissions (string literal in code, not executed)sudo chown -R deploy:deploy /opt/{project_name} /opt/backupcode literal -
low Dangerous commands
cmd-privilegescripts/generate-setup-guide.py:182Privilege escalation / world-writable permissions (string literal in code, not executed)sudo cp {project_name}.service /etc/systemd/system/code literal -
low Dangerous commands
cmd-background-processscripts/generate-setup-guide.py:184Starts a background / autostarted process (string literal in code, not executed)sudo systemctl enable {project_name}code literal -
low Dangerous commands
cmd-background-processscripts/generate-setup-guide.py:257Starts a background / autostarted process (string literal in code, not executed)sudo systemctl enable docker
code literal
Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: CI/CD workflow skill for Java + Vue projects. Supports GitLab CI a… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
missing-refreference to a missing file: assets/gitlab-ci.yml.txt
Process rating: all ten parameters 53/100
- 0Tools and files. 1 referenced file(s) missing: assets/gitlab-ci.yml.txt
- 0Result and completion. Does not say what the result is
- 30Running it twice. 34 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 113 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3034 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 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
- -31 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 478: enough signal without eating the budget
- +4Structure: 43 headings
- +3Step-by-step instructions: 113 items
- +4Has examples (15 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.