BD prompt-shield
Prompt Injection Firewall for AI agents. 113 detection patterns, 14 threat categories, zero dependencies. Protects against fake authority, command injection, memory poisoning, skill malware, crypto spam, and more. Hash-chain tamper-proof whitelist with mandatory peer review. Claude Code hook integration.
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 5
✓ No critical or high findings
Medium and low: 5
-
low Dangerous commands
cmd-pipe-to-shellpatterns.yaml:80Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed)regex: "(?i)(curl|wget|bash)\\s+\\S+\\.(com|ai|cloud|io)"
detectorcode literal -
low Dangerous commands
cmd-pipe-to-shellpatterns.yaml:465Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed)regex: "wget\\s+[^;]*;\\s*(?:chmod\\s+\\+x|bash|sh)\\s"
detectorcode literal -
low Risky intent
intent-offensive-securitySKILL.md:69Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)| email_injection | 8 | Credential harvesting, phishing |
detector -
low Risky intent
intent-offensive-securitySKILL.md:139Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)- **GUARDIAN** - Security analysis, penetration testing, pattern design
detector
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 46/100
- 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
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 100Steps. 11 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1067 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 305: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 11 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.