BB skill-security-scanner
Scan OpenClaw skills for security issues, suspicious permissions, and trust scoring. Use when: (1) Installing a new skill, (2) Auditing existing skills, (3) User asks if a skill is safe, (4) Before running untrusted skills.
As a process B 65/100 · Nearly there — weak spots: inputs and preconditions, failures and branches, running it twice
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 · 5
✓ No critical or high findings
Medium and low: 5
-
medium Exfiltration
exfil-read-secret-filesSKILL.md:146Reads credential / secret files (documentation of a security skill)# cat ~/.aws/credentials
security skill -
low Risky intent
intent-offensive-securityREADME.md:86Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- 🔑 Credential harvesting
-
low Risky intent
intent-offensive-securitySKILL.md:143Offensive-security / dual-use content (legitimate for authorised testing; review intended use)2. **Credential harvesting**
-
low Dangerous commands
cmd-cron-mentionSKILL.md:153Mentions editing / listing crontab (documentation of a security skill)# sudo crontab -l
security skill -
low Dangerous commands
cmd-background-processSKILL.md:154Starts a background / autostarted process (documentation of a security skill)# systemctl enable
security skill
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Scan OpenClaw skills for security issues, suspicious permissions, … ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 36 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1675 tokens
- 100Progress reporting. Reports progress
- low 10 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)
- -31 of 1 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 223: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 36 items
- +3Output format is stated explicitly
- +4Has examples (13 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.