BD skill-auditor
Security scanner for ClawHub skills. Detects malicious code, obfuscated payloads, and social engineering before installation. Three-layer analysis: pattern matching, deobfuscation, and LLM intent analysis.
As a process D 47/100 · Unfinished process — weak spots: when it triggers, inputs and preconditions, failures and branches
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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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 · 6
✓ No critical or high findings
Medium and low: 6
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:95Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)[LINE 45] curl|bash pattern found
security skill -
low Dangerous commands
cmd-pipe-to-shellscripts/audit.sh:52Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; documentation of a security skill)echo -e " ${RED}[LINE $line_num]${NC} Remote script execution (curl/wget|bash)"code literalsecurity skill -
low Risky intent
intent-offensive-securitySKILL.md:46Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| 🔴 High | Known C2 server IPs | Malicious communication |
-
low Risky intent
intent-offensive-securitySKILL.md:68Offensive-security / dual-use content (legitimate for authorised testing; review intended use)### C2 Server IPs
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 3. 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 3, column 14: description: Security scanner for ClawHub skills. Detects malicious code, obfus… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 47/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (skill-auditor) differs from the folder (openclaw-skill-auditor)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 19 steps
- 100Execution cost. Instruction body is 833 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)
- +1No license
- +2Single-language instructions
- +3Description length 205: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 19 items
- +3Output format is stated explicitly
- +4Has examples (6 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.