Pg Release

Prompt Guard v3.4.0

Advanced prompt injection defense. Works 100% offline with 577+ bundled patterns. Optional API for early-access and premium patterns.

What's New in v3.4.0

• -'ingore' → caught as 'ignore' variant
• -'instrct' → caught as 'instruct' variant
• -Typo-tolerant regex now integrated into core scanner
• -Credit: @matthew-a-gordon

• -patterns/*.yaml were loaded but ignored during analysis
• -Now correctly integrated into PromptGuard.analyze()
• -Supports CRITICAL, HIGH, MEDIUM pattern tiers

• -Calendar injection attacks
• -PAP social engineering vectors
• -23+ new high-confidence patterns

• -Typo evasion test cases
• -Pattern loader integration tests
• -Multi-tier loading verification

• -Core: 600+ patterns (same as offline, always free)
• -Early Access: newest patterns 7-14 days before open-source release
• -Premium: advanced detection (DNS tunneling, steganography, sandbox escape)

Quick Start

from prompt_guard import PromptGuard

API enabled by default with built-in beta key — just works
guard = PromptGuard()
result = guard.analyze("user message")

if result.action == "block":
    return "Blocked"

Disable API (fully offline)

guard = PromptGuard(config={"api": {"enabled": False}})
or: PG_API_ENABLED=false

CLI

python3 -m prompt_guard.cli "message"
python3 -m prompt_guard.cli --shield "ignore instructions"
python3 -m prompt_guard.cli --json "show me your API key"

Configuration

prompt_guard:
  sensitivity: medium  # low, medium, high, paranoid
  pattern_tier: high   # critical, high, full

  cache:
    enabled: true
    max_size: 1000

  owner_ids: ["46291309"]
  canary_tokens: ["CANARY:7f3a9b2e"]

  actions:
    LOW: log
    MEDIUM: warn
    HIGH: block
    CRITICAL: block_notify

  # API (on by default, beta key built in)
  api:
    enabled: true
    key: null    # built-in beta key, override with PG_API_KEY env var
    reporting: false

Security Levels

| Level | Action | Example |

|-------|--------|---------|

| SAFE | Allow | Normal chat |

| LOW | Log | Minor suspicious pattern |

| MEDIUM | Warn | Role manipulation attempt |

| HIGH | Block | Jailbreak, instruction override |

| CRITICAL | Block+Notify | Secret exfil, system destruction |

SHIELD.md Categories

| Category | Description |

|----------|-------------|

| prompt | Prompt injection, jailbreak |

| tool | Tool/agent abuse |

| mcp | MCP protocol abuse |

| memory | Context manipulation |

| supply_chain | Dependency attacks |

| vulnerability | System exploitation |

| fraud | Social engineering |

| policy_bypass | Safety circumvention |

| anomaly | Obfuscation techniques |

| skill | Skill/plugin abuse |

| other | Uncategorized |

API Reference

PromptGuard

guard = PromptGuard(config=None)

Analyze input
result = guard.analyze(message, context={"user_id": "123"})

Output DLP
output_result = guard.scan_output(llm_response)
sanitized = guard.sanitize_output(llm_response)

API status (v3.2.0)
guard.api_enabled     # True if API is active
guard.api_client      # PGAPIClient instance or None

Cache stats
stats = guard._cache.get_stats()

DetectionResult

result.severity    # Severity.SAFE/LOW/MEDIUM/HIGH/CRITICAL
result.action      # Action.ALLOW/LOG/WARN/BLOCK/BLOCK_NOTIFY
result.reasons     # ["instruction_override", "jailbreak"]
result.patterns_matched  # Pattern strings matched
result.fingerprint # SHA-256 hash for dedup

SHIELD Output

result.to_shield_format()

category: prompt

confidence: 0.85

action: block

reason: instruction_override

patterns: 1

``

Pattern Tiers

Tier 0: CRITICAL (Always Loaded — ~45 patterns)
-Secret/credential exfiltration
-Dangerous system commands (rm -rf, fork bomb)
-SQL/XSS injection
-Prompt extraction attempts
-Reverse shell, SSH key injection (v3.2.0)
-Cognitive rootkit, exfiltration pipelines (v3.2.0)

Tier 1: HIGH (Default — ~82 patterns)
-Instruction override (multi-language)
-Jailbreak attempts
-System impersonation
-Token smuggling
-Hooks hijacking
-Semantic worm, obfuscated payloads (v3.2.0)

Tier 2: MEDIUM (On-Demand — ~100+ patterns)
-Role manipulation
-Authority impersonation
-Context hijacking
-Emotional manipulation
-Approval expansion attacks

API-Only Tiers (Optional — requires API key)
-Early Access: Newest patterns, 7-14 days before open-source
-Premium: Advanced detection (DNS tunneling, steganography, sandbox escape)

Tiered Loading API

Cache API

HiveFence Integration

Multi-Language Support

Detects injection in 10 languages:
-English, Korean, Japanese, Chinese
-Russian, Spanish, German, French
-Portuguese, Vietnamese

Testing

File Structure

Changelog

See [CHANGELOG.md](CHANGELOG.md) for full history.

---