grey-panda 1.0.0

A zero-dependency, standards-anchored AI security toolkit that any developer or security reviewer can run in seconds — in the IDE, in CI, or from the terminal.

Quick start · The bundle · How it works · Standards · In your IDE · Honest limits · Contributing

---

"Stop trying to build a model that cannot be fooled. Build the system around it, so that when the model is fooled — and it will be — nothing important breaks."

Grey Panda makes the secure path the easy path for anyone building LLM-powered, agentic, or Model Context Protocol (MCP) features — from a solo indie developer to an enterprise AppSec team.

⚡ Quick start

pip install grey-panda        # pure Python, zero dependencies
gp scan .                     # scan your repo — real findings, beautiful report

Add drop-in guardrails to an existing LLM call in under two minutes — you never rewrite the call, you wrap it:

from greypanda import PromptGuardrail, DLPScanner, OutputGuardrail

guard, dlp, out = PromptGuardrail(), DLPScanner(), OutputGuardrail()

safe   = guard.assert_safe(user_input)        # block known injection + strip invisible Unicode
clean  = dlp.redact(safe)                       # remove PII & secrets before the model sees them
reply  = call_your_llm(clean)                   # ← your existing call, unchanged
answer = out.sanitize(reply).sanitized_text     # block data-exfil URLs & unsafe HTML

---

🎯 Why this exists

Prompt injection is the #1 AI attack pattern and it needs no authentication (OWASP LLM01). Agentic systems can take an irreversible action from a single injected instruction. And MCP has opened a whole new surface — tool poisoning and rug pulls. Your existing AppSec tools don't see any of it.

🐼 The idea: one calm guardian

Grey Panda keeps two rare qualities as non-negotiable: intellectual honesty (a whole doc on what it can and cannot do) and standards-anchoring (every rule cites an OWASP ID). No neon-hacker theatre — just controls that are a joy to adopt.

📦 What's in the bundle

Five audience-facing module kits, all powered by one shared, zero-dependency engine:

Kit	For	Start here
🧰 Module 1 — Developer Kit	Building AI features	Drop-in SDK + IDE integration
🛡️ Module 2 — Security Reviewer Kit	Reviewing / gating	AISVS verify, threat models, sign-off
🔍 Module 3 — Scanner & CI/CD Kit	Platform / DevOps	26 rules, SARIF, GitHub Action
🤖 Module 4 — MCP & Agent Security Kit	Agents & MCP	Rule of Two, HITL, manifest pinning, ACS
📚 Module 5 — Standards & Governance Kit	Everyone / compliance	Knowledge pack, mappings, Can/Cannot-Do

⚙️ How it works

Defense in depth, not prevention theatre. Full walkthrough: HOW-TO-add-guardrails · architecture: docs/ARCHITECTURE.md.

🔐 Standards-anchored

Every rule, checklist item, and SDK control cites a specific ID. Explore any control from the CLI:

gp standards LLM01:2026      # explain a control + its Grey Panda fix
gp standards                 # list every standard and control ID

Full mapping tables: Module 5 → mappings/.

✅ Proof

See the before/after for yourself — the same app, insecure vs. rebuilt with Grey Panda controls:

gp scan examples/vulnerable_app --profile enterprise    # 🔴 findings
gp scan examples/secure_app     --profile enterprise    # ✅ clean

👥 For everyone

gp scan . --profile solo          # high-signal core, fail on CRITICAL
gp init  . --profile team         # scaffold config + GitHub Action + pre-commit
gp verify . --level 2             # AISVS Level 2 verification report

More: Module 1 → PROFILES.

🚀 Get started

pip install grey-panda           # from PyPI
pipx install grey-panda          # isolated CLI
uvx grey-panda scan .            # zero-install run

Command	Does
gp scan [path]	Scan for AI/agent/MCP issues (--profile, --format md/json/sarif, --fail-on)
gp init [path]	Scaffold config, GitHub Action, and pre-commit into a repo
gp verify [path]	AISVS Level 1/2/3 verification report
gp checklist	Print the AI security checklist
gp standards [id]	List or explain standards / control IDs
gp agbom <agent>	Emit an Agent Bill of Materials
gp mcp	Run Grey Panda as an MCP server (stdio)
gp doctor	Environment self-check + honest-limits pointer

🤝 In your IDE

Grey Panda secures MCP — and ships as an MCP server, so Claude Code, Cursor, Windsurf, or VS Code can call it while you code:

{ "mcpServers": { "grey-panda": { "command": "gp", "args": ["mcp"] } } }

Then ask your assistant to "review this file with grey panda" or "explain LLM03". Details: Module 1 → HOW-TO-use-in-your-ide and Module 4 → HOW-TO-run-the-mcp-server.

🧭 Honest about limits

Grey Panda is a strong floor, not a ceiling. Pattern matching cannot stop all prompt injection; regex DLP is language-specific; static analysis has false positives and negatives. We ship a whole document — with a confidence level and failure condition for every capability: WHAT_IT_CAN_AND_CANNOT_DO.md. Read it before you rely on the tool.

🌱 Contributing

Adding a scanner rule is editing one dataclass with a bad + good example — see CONTRIBUTING.md and Module 3 → HOW-TO-write-a-rule. Everyone is welcome under our Code of Conduct. Found a vulnerability in Grey Panda itself? See SECURITY.md.

Build from source:

git clone https://github.com/dibakshya01/grey-panda && cd grey-panda
pip install -e ".[dev]"
python -m unittest discover -s tests        # zero-dependency test suite
gp scan . --profile enterprise --fail-on HIGH   # Grey Panda scans itself, clean

📄 License

Apache-2.0. Standards cited are the property of their respective authors (see NOTICE). OWASP® is a registered trademark of the OWASP Foundation; Grey Panda is an independent, community project and is not affiliated with or endorsed by OWASP.

_{🐼 Grey Panda — make the secure path the easy path.}