CD iterate
Fully automated multi-round code iteration with configurable N-dimension parallel review, onboarding/personalization, and a cross-assistant installer/update system with mandatory SHA256 checksum verification. v3.0 adds a dual-mode (the original iterate mode plus a defensive-programming mode via /iterate defensive) that performs normal incremental coding tasks with defensive discipline end-to-end.
Fully automated multi-round code iteration with configurable N-dimension parallel review, onboarding/personalization, and a cross-assistant installer/update…
As a process D 35/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 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.
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.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 5
✓ No critical or high findings
Medium and low: 5
-
medium Exfiltration
net-redirectable-api-keynpm-installer/lib/installer.js:39Helper 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-shell-known-hostREADME.md:82Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/jingzhao-l/iterate-harness/main/scripts/install.sh | bash
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostREADME.zh-CN.md:78Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/jingzhao-l/iterate-harness/main/scripts/install.sh | bash
-
low Dangerous commands
cmd-background-processDESIGN-iterate-harness.md:805Starts a background / autostarted process (detector / deny-list definition)4. **cron 守护进程 Windows 不兼容**（[cron_scheduler.py](file:///Volumes/Eng-Dev/iterate-skill/harness/iterate-harness/src/iterate_harness/services/cron_scheduler.py)）：`start_daemon` 用 Unix 专属 `os.fork()`+`os
detector -
low Dangerous commands
cmd-background-processiterate_cli/guard.py:83Starts a background / autostarted process (string literal in code, not executed; documentation of a security skill)"disown",
code literalsecurity skill
Files scanned: 64. 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") - warning
body-longSKILL.md body ≈ 13481 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "permissions" - note
edit-residuethe text marks something as outdated (lines 666): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 35/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 45 mutating operations with no state check
- 40Consistency. Frontmatter name (iterate) differs from the folder (iterate-skill)
- 40Execution cost. Instruction body is 13481 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, git, python, node) that frontmatter does not declare
- 85Steps. 311 steps, 2 vague phrases
- 100Progress reporting. Reports progress
- low 18 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (26 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
- -5TODO / placeholder text left in the skill
- -31 of 4 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 399: enough signal without eating the budget
- +4Structure: 49 headings
- +3Step-by-step instructions: 311 items
- +4Has examples (16 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 52.