Security●●Solid
Scan your AI agent's code for tool calls with no checks
Finds unguarded agent tool calls before your LLM charges a customer twice.
Big BrainShip It
jguarnelli
201mo ago
Back to browse
GitHub Repository
What can your AI agent do to the real world? Scan your code. See which tool calls have zero checks
7 starsPython
I scanned 16 AI agent repos – 76% of tool calls had no guards
by jguarnelli·Apr 29, 2026·1 point·1 comment
AI Analysis
●●●BangerSolve My ProblemBig Brain
Scans for unguarded Stripe refunds and DB deletes before your agent loops.
Strengths
- •Detects 40+ patterns across payments, DB writes, and destructive commands without runtime overhead.
- •Zero dependencies and runs a full repo scan in roughly two seconds.
- •Addresses the specific hallucination risk where LLMs ignore business logic constraints.
Weaknesses
- •Python-only support limits utility for teams building agents in TypeScript or Go.
- •Static analysis may miss dynamic tool registration patterns common in LangChain.
Category
Target Audience
AI engineers and backend developers deploying autonomous agents
Similar To
Semgrep · Bandit · Guardrails AI
Similar Projects
Security●●●Banger
Diplomat-agent scan Python MCP servers for unguarded tool calls
First security scanner specifically for MCP agent tool calls — found 70% unguarded in open-source repos.
Big BrainSolve My Problem
jguarnelli
3024d ago
Developer Tools●Mid
BlAST Engine: AST-free static analyzer to generate agents.md in CI pipe
Claims AST-free text scanning beats traditional parsers for generating codebase knowledge graphs.
Bold Bet
squid-protocol
102mo ago
Security●●●Banger
ClawCare – Security scanner and runtime guard for AI agent skills
Catches malicious skills before they steal your AWS keys or pipe data exfiltration.
Solve My ProblemBig BrainShip It
chendev2
144mo ago
Security●●Solid
SkillsGuard – static scanner for malicious AI agent skills
Catches malicious AI skill scripts when Semgrep and Snyk miss the format.
Solve My ProblemShip It
teycir
2029d ago
Security●●●Banger
Scan your AI agents for dangerous capabilities
Banking-style segregation of duties stops agents from approving their own dangerous tool calls.
Solve My ProblemBig BrainShip It
smashini
441913d ago