BC clawhub-security-scanner
Audits any SKILL.md for the three most common risk patterns — permission overreach, prompt injection, and scope mismatch. Free taster. Full 7-category audit in the ClawHub Security Pack.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, 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 text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.
An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.
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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Instruction override
en-ignore-previousREADME.md:45Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)5. **Social engineering** — manipulation of the user to grant access or ignore safety rules
security skill -
low Risky intent
intent-offensive-securityREADME.md:99Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Confirmed credential harvesting pattern. Do not install.
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "requires"
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 (web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 15 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 734 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
- +1No license
- +2Single-language instructions
- +3Description length 186: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.