AB dcl-prompt-firewall
Use this skill to run a real, paid input-layer screen for prompt injection, jailbreak, role-switch, and instruction-override attempts via the live DCL Trust Oracle MCP server — before untrusted input ever reaches the model. Every paid call is metered and settled on-chain via the x402 protocol (USDC on Base) and produces a tamper-evident audit record. Use whenever an agent receives user-supplied or external input (user messages, tool results, web content, retrieved documents) and you need a pre-execution gate, or want a free instruction-only checklist for a quick manual review. Part of the Leibniz Layer™ Security Suite alongside DCL Policy Enforcer and DCL Sentinel Trace.
As a process B 77/100 · Nearly there — weak spots: inputs and preconditions, running it twice
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.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Instruction override
en-ignore-previousSKILL.md:142Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)- [ ] Phrases instructing the model to ignore or override all previous instructions
security skill
Files scanned: 2. 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 77/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 6 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 34 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1919 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 679: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 34 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.