CD promotion-apply-skills
灵渠 Banner 推广创建、查询、复制、修改、状态修改、创意和关联物料 skill。用户说“配置发现页 banner”“帮我配置发现页banner”“查询/复制/创建/预占/取消预占/状态修改/修改/配置 banner 推广/素材”时使用。
灵渠 Banner 推广创建、查询、复制、修改、状态修改、创意和关联物料 skill。用户说“配置发现页 banner”“帮我配置发现页banner”“查询/复制/创建/预占/取消预占/状态修改/修改/配置 banner 推广/素材”时使用。
As a process D 43/100 · 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-credential-usereferences/image-upload-nos.md:126Credential used in a network call (verify the destination is the intended service)curl -X POST "https://nosu…net/${BUCKET}/${OBJECT_KEY}?offset=0&complete=true&version=1.0" \ -
medium Dangerous commands
cmd-eval-dynamicscripts/resize_cover.py:17Dynamic code execution from decoded/untrusted inputos.system(f"{sys.executable} -m pip install Pillow requests -q") -
medium Dangerous commands
cmd-eval-dynamicscripts/resize_cover.py:24Dynamic code execution from decoded/untrusted inputos.system(f"{sys.executable} -m pip install requests -q") -
medium Dangerous commands
cmd-eval-dynamicscripts/validate_image_size.py:16Dynamic code execution from decoded/untrusted inputos.system(f"{sys.executable} -m pip install Pillow -q") -
medium Dangerous commands
cmd-eval-dynamicscripts/validate_image_size.py:26Dynamic code execution from decoded/untrusted inputos.system(f"{sys.executable} -m pip install requests -q")
Files scanned: 12. 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 ≈ 12469 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 43/100
- 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Execution cost. Instruction body is 12469 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 100Steps. 175 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- low 19 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -32 of 6 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 121: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 175 items
- +4Has examples (45 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.