BB clawguard-auditor
ClawGuard v3 Auditor - 企业级 Skill 安全审计器，支持意图偏离检测、SAST、供应链安全、ML 异常检测。当用户要求审计、检测、安装前检查一个 Skill 的安全性时触发。
As a process B 70/100 · Nearly there — weak spots: when it triggers
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.
How to improve
- 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 · 7
✓ No critical or high findings
Medium and low: 7
-
medium Exfiltration
exfil-read-secret-filesREADME.md:30Reads credential / secret files (documentation of a security skill)代码: fs.readFileSync('/.ssh/id_rsa')security skill -
medium Exfiltration
exfil-read-secret-filesSKILL.md:554Reads credential / secret files (documentation of a security skill)Evidence: readFile('~/.ssh/id_rsa')security skill -
low Risky intent
intent-offensive-securitySKILL.md:248Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Reverse shell signatures | CRITICAL | T1059.004 |
-
low Risky intent
intent-offensive-securitySKILL.md:251Offensive-security / dual-use content (legitimate for authorised testing; review intended use)#### Reverse Shell Signatures (Enhanced Detection)
-
low Risky intent
intent-offensive-securitySKILL.md:254Offensive-security / dual-use content (legitimate for authorised testing; review intended use)// Comprehensive reverse shell patterns
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 10. 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 70/100
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 4 branches
- 70Execution cost. Instruction body is 4897 tokens
- 100Steps. 32 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- low 15 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
- +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 100: 120–800 characters recommended
- -218 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +4Structure: 57 headings
- +3Step-by-step instructions: 32 items
- +3Output format is stated explicitly
- +4Has examples (13 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.