CF night-shift
Queue coding plans during the day, approve them, execute later in isolated worktrees, and inspect reports. Background agentic execution requires an explicitly configured non-interactive runner.
As a process F 56/100 · Will not run — References files that are not bundled: scripts/test_queue.py, scripts/test_integration.py
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.
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 · 3
-
high Dangerous commands
cmd-destructive-fsscripts/verifier.py:30Destructive filesystem command (wipes root/home/drive) (string literal in code, not executed)":(){ :|:& };:": "Fork bomb",code literal -
high Dangerous commands
cmd-destructive-fsscripts/verifier.py:36Destructive filesystem command (wipes root/home/drive) (string literal in code, not executed)":(){:|:&};:": "Fork bomb (alternate)",code literal
Medium and low: 1
-
low Dangerous commands
cmd-privilegescripts/verifier.py:31Privilege escalation / world-writable permissions (string literal in code, not executed)"chmod 777 /": "Root permission escalation",
code literal
Files scanned: 21. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/test_queue.py - warning
missing-refreference to a missing file: scripts/test_integration.py
Process rating: all ten parameters 56/100
- 0Tools and files. 2 referenced file(s) missing: scripts/test_queue.py, scripts/test_integration.py
- 0Result and completion. Does not say what the result is
- 30Running it twice. 16 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 251 steps, 3 vague phrases
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3882 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 17 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (5 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)
- +3Output format is not stated: the model decides each time
- -32 of 16 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 193: enough signal without eating the budget
- +4Structure: 59 headings
- +3Step-by-step instructions: 251 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.