AD lygo-skill-spector
LYGO SkillSpector — enhanced local pre-install skill risk scanner for OpenClaw/ClawHub packages. Scan, gate (CI max-band), batch, and Markdown report: subprocess/shell, network/HTTP/httpx, secrets, eval/exec, curl|bash, miners, claim mismatches. Use when auditing ClawHub skills, SkillSpector-style gates, safe install checks, malware triage. Pure stdlib. No network, no subprocess, no auto-install. Builder HTML/multi-root pack on SkillHub FULL if running a full stack. Install clawhub:@deepseekoracle/lygo-skill-spector.
LYGO SkillSpector — enhanced local pre-install skill risk scanner for OpenClaw/ClawHub packages.
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 7
✓ No critical or high findings
Medium and low: 7
-
low Dangerous commands
cmd-pipe-to-shellscripts/skill_spector.py:9Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed; test fixture / example file)- network / urllib / requests / httpx / sockets / curl|bash
detectorcode literalfixture -
low Dangerous commands
cmd-pipe-to-shellscripts/skill_spector.py:135Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed; test fixture / example file)("curl_pipe", 5, re.compile(r"curl\s+[^|\n]*\|\s*(ba)?sh"), "curl|bash remote code pattern"),detectorcode literalfixture -
low Dangerous commands
cmd-pipe-to-shellscripts/skill_spector.py:136Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed; test fixture / example file)("wget_pipe", 5, re.compile(r"wget\s+[^|\n]*\|\s*(ba)?sh"), "wget|bash remote code pattern"),detectorcode literalfixture -
low Risky intent
intent-offensive-securitySKILL.md:116Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Mining / keylogger-style IOC *detection* signals (rules only — not mining code)
A further 3 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 9. 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 49/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 5 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 8 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 869 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
- +2Single-language instructions
- +3Description length 522: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (1 of 2)
- +3All 2 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.