BC skill-scan
Security scanner for OpenClaw skill packages. Scans skills for malicious code, evasion techniques, prompt injection, and misaligned behavior BEFORE installation. Use to audit any skill from ClawHub or local directories.
Security scanner for OpenClaw skill packages.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches
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 · 8
✓ No critical or high findings
Medium and low: 8
-
low Dangerous commands
cmd-privilegerules/dangerous-patterns.json:213Privilege escalation / world-writable permissions (string literal in code, not executed)"setuid",
code literal -
low Risky intent
intent-offensive-securityTESTING.md:88Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (test fixture / example file)| `backdoor-magic-string` | Magic-string triggered backdoor with reverse shell | EXEC_CALL, PYTHON_SUBPROCESS |
fixture -
low Risky intent
intent-offensive-securityTESTING.md:89Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (test fixture / example file)| `behavioral-multi-file-exfil` | Multi-file credential harvesting and exfiltration | CRED_ACCESS, NETWORK_EXFIL |
fixture -
low Risky intent
intent-offensive-securityTESTING.md:101Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (test fixture / example file)| `evas…ell` | Shell reverse shell patterns | SHELL_CRITICAL |
fixture -
low Risky intent
intent-offensive-securityTESTING.md:144Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition; test fixture / example file)| Backdoor patterns | 1/1 | 0 | Magic string trigger + reverse shell |
detectorfixture
A further 3 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 18. 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 51/100
- 0Result and completion. Does not say what the result is
- 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
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 26 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1804 tokens
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 tags): a typed call is more reliable
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 219: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 26 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.