BC skill-security-review
Review the security of an OpenClaw skill or agent before installation, import, activation, or trust. Use when the user asks whether a skill is safe, asks to review a .skill package, asks whether a GitHub/ClawHub/zip-based skill is safe, or expresses intent to install/import/enable a skill. Default behavior: if the user wants to install a skill, audit first, then present the verdict and ask for confirmation before installing. Focus on data exposure, local command execution, persistence, network access, privilege escalation, destructive behavior, and supply-chain risk.
As a process C 62/100 · Has gaps — weak spots: inputs and preconditions, running it twice, progress reporting
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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Risky intent
intent-offensive-securityreferences/checklist.md:17Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Privilege escalation request
-
low Risky intent
intent-offensive-securityskill-card.md:2Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Reviews OpenClaw skills or agents before installation or activation, focusing on data exposure, code execution, persistence, network access, privilege escalation, destructive behavior, and supply-chai
-
low Risky intent
intent-offensive-securitySKILL.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use)description: Review the security of an OpenClaw skill or agent before installation, import, activation, or trust. Use when the user asks whether a skill is safe, asks to review a .skill package, asks
Files scanned: 4. 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: Review the security of an OpenClaw skill or agent before installat… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 62/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 65Failures and branches. 3 branches
- 70When it triggers. States when to use, but not when not to
- 85Steps. 64 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1342 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +4No input/output examples
- +2Single-language instructions
- +3Description length 573: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 64 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (1 of 1)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.