AD skill-security-check
Skill 发布前安全检查工具。在发布 skill 到 ClawHub 前，自动扫描敏感信息（API Key、Token、私钥、邮箱、手机号、精确坐标等）。Use before publishing any skill to prevent leaking private data.
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
For the model run — optional
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Secrets in code
secret-password-literalSKILL.md:51Hard-coded password / key literal (may be an example) (placeholder value)./my-skill/script.py:api_key = "sk-a…..."
placeholder -
low Secrets in code
secret-password-literalSKILL.md:76Hard-coded password / key literal (may be an example) (placeholder value)API_KEY = "sk-a…..."
placeholder
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 49/100
- 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
- 40Consistency. Frontmatter name (skill-security-check) differs from the folder (pre-publish-security-check)
- 100Tools and files. No external tools needed
- 100Steps. 5 steps
- 100Execution cost. Instruction body is 407 tokens
- 100Running it twice. No mutating operations
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
- +1No license
- +2Single-language instructions
- +3Description length 142: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 5 items
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.
External checks
ClawHub: clean
This is a local pre-publish checker that scans a user-chosen skill folder for possible secrets, with no evidence of hidden networking, persistence, or destructive behavior.
LLM: benign (high) · VirusTotal: · 29 May 2026