BD skill-security
Security audit tool for OpenClaw skills. Scans for credential harvesting, code injection, network exfiltration, obfuscation. ALWAYS run before installing any new skill from external sources. Triggers on: new skill installation, skill audit, security scan, skill review, before loading external skill.
As a process D 49/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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-securityskill-card.md:2Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)Security audit tool for OpenClaw skills that scans for credential harvesting, code injection, network exfiltration, and obfuscation before installing or reviewing external skills. <br>
detector -
low Risky intent
intent-offensive-securitySKILL.md:4Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)Security audit tool for OpenClaw skills. Scans for credential harvesting, code injection,
detector -
low Risky intent
intent-offensive-securitySKILL.md:29Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| **Credential Harvesting** | 🚨 HIGH | `.ssh/`, `.aws/`, `pass `, `keyring`, `credential`, `secret`, `token` file reads |
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
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
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 13 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 681 tokens
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
- -219 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 300: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 13 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.