CF deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack for a new platform.
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any…
As a process F 26/100 · No process to follow — References files that are not bundled: ../README.md
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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
- 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 · 7
✓ No critical or high findings
Medium and low: 7
-
medium Dangerous commands
cmd-pipe-to-shellDockerfile:273Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)# flag — `curl …/install | bash` always fetches `latest`, so the image was
quoted -
medium Exfiltration
net-redirectable-api-keyentrypoint.py:136Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Dangerous commands
cmd-pipe-to-shellREADME.md:459Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)image); the other vendor-installer rows run the harness's own `curl | bash`
quoted -
low Exfiltration
read-dotenvbootstrap.sh:27Reads a .env filecp .env.example .env
-
low Exfiltration
read-dotenvdocker-compose.yaml:6Reads a .env file (code comment)# cp .env.example .env # edit POSTGRES_PASSWORD at minimum
comment -
low Exfiltration
read-dotenvREADME.md:25Reads a .env file (quoted — discussed, not commanded)alone. If you prefer to manage `.env` yourself, just `cp .env.example
quoted -
low Exfiltration
read-dotenvSKILL.md:33Reads a .env filecp .env.example .env # edit POSTGRES_PASSWORD at minimum
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../README.md
Process rating: all ten parameters 26/100
- 0Tools and files. 1 referenced file(s) missing: ../README.md
- 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
- 30Running it twice. 10 mutating operations with no state check
- 40Consistency. Frontmatter name (deploy-docker-compose) differs from the folder (docker)
- 50Steps. 2 steps
- 70When it triggers. States when to use, but not when not to
- 100Execution cost. Instruction body is 1153 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)
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 338: enough signal without eating the budget
- +4Structure: 7 headings
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.