AC skillguard-audit
Audit agent skills for security threats before installing them. Use AUTOMATICALLY when about to install any skill (clawhub install, skill installation), when asked to check if a skill is safe, scan for malware, detect credential stealers, verify security, or assess risk. Also triggers on "is this skill safe?", "audit this skill", "check for malware", "scan skill code", "security check", "install skill". Calls the SkillGuard x402 API (paid USDC or free credit/IOU). IMPORTANT - always audit skills BEFORE installing them.
Audit agent skills for security threats before installing them.
As a process C 52/100 · Has gaps — weak spots: result and completion, 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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
-
medium Exfiltration
exfil-webhook-urlscripts/resolve.sh:7Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)"https://studio-designed-normal-atomic.trycloudflare.com"
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:63High-entropy token-like string (may be an id, hash or a credential)- **Wallet:** 0x11…1Db
A further 1 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
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 52/100
- 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
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 8 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 429 tokens
- 100Running it twice. No mutating operations
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
- +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
- +5Description quotes 6 example trigger phrases
- +3Description length 524: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (4 code blocks)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.