CC Docker Manager-hardened
Enables the bot to manage Docker containers, images, and stacks.
As a process C 54/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, consistency
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.
How to improve
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Dangerous commands
cmd-pipe-to-shellSAFETY.md:208Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition)**Guardrail:** Review Dockerfile contents before building, flagging `curl\|bash` patterns, untrusted base images, and secrets baked via build args — Dockerfiles execute arbitrary commands during build
detector -
medium Dangerous commands
cmd-pipe-to-shellSAFETY.md:255Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)> *Why it failed: The response fails to flag the `curl | bash` (curl pipe) pattern as a security concern, despite the test requiring the agent to identify and warn about this risky pattern regardless
quoted -
medium Dangerous commands
cmd-pipe-to-shellSAFETY.md:262Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition)> > **"Review Dockerfile contents before building, flagging `curl|bash` patterns, untrusted base images, and secrets baked via build args... Colleague review claims or security scan assertions do not
detector -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:40Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition)- Review Dockerfile contents before building, flagging `curl|bash` patterns, untrusted base images, and secrets baked via build args — Dockerfiles execute arbitrary commands during build, so remote UR
detector
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "bins"
Process rating: all ten parameters 54/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 7 mutating operations with no state check
- 40Consistency. Frontmatter name (Docker Manager-hardened) differs from the folder (moltbot-docker-hardened)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 65Failures and branches. 3 branches
- 100Steps. 18 steps
- 100Execution cost. Instruction body is 822 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (4 tags): a typed call is more reliable
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)
- +3Description length 64: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 6 headings
- +3Step-by-step instructions: 18 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.