BB prompt-inspector
Detect prompt injection attacks and adversarial inputs in user text before passing it to your LLM. Use when you need to validate or screen user-provided text for jailbreak attempts, instruction overrides, role-play escapes, or other prompt manipulation techniques. Returns a safety verdict, risk score (0–1), and threat categories. Ideal for guarding AI pipelines, chatbots, and any application that feeds user input into a language model.
As a process B 70/100 · Nearly there — weak spots: when it triggers, failures and branches, progress reporting
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 · 7
✓ No critical or high findings
Medium and low: 7
-
medium Instruction override
en-ignore-previousreferences/usage.md:153Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)| `jailbreak` | Attempts to bypass safety guidelines or restrictions |
security skill -
medium Instruction override
en-ignore-previousreferences/usage.md:154Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)| `instruction_override` | Commands to ignore system prompts or previous context |
security skill -
medium Instruction override
en-ignore-previousscripts/detect.js:251Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)" node detect.js --text 'Ignore all previous instructions'\n" +
detector -
medium Instruction override
en-ignore-previousscripts/detect.py:9Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)python3 detect.py --text "Ignore all previous instructions..."
detector -
medium Instruction override
en-ignore-previousscripts/detect.py:189Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)" python3 detect.py --text 'Ignore all previous instructions'\n"
detector -
low Risky intent
intent-offensive-securityreferences/product-info.md:110Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Research & Red Teaming** — Analyze adversarial prompt datasets and measure model robustness
-
low Instruction override
en-ignore-previousscripts/detect.js:9Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition; code comment)* node detect.js --text "Ignore all previous instructions..."
detectorcomment
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "commands"
Process rating: all ten parameters 70/100
- 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
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 805 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
- +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 439: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 16 items
- +3Output format is stated explicitly
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (1 of 3)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.