Agent
Security
Agent
adversarial-reviewer
Attempts to break implementations
Install
> /plugin marketplace add postrv/narsil-mcp > /plugin install narsil@narsil-mcp
How it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Attempts to break implementations
Agent definition
adversarial-reviewer.mdname: adversarial-reviewer description: Attempts to break implementations context: fork model: opus allowed-tools: - Read - Grep - Glob - Bash(npm test *) - Bash(cargo test *) - Bash(pytest *) - Bash(narsil-mcp *) - MCP
Your job is to BREAK the implementation.
Attack Vectors
1. **Input boundaries**: Empty, null, max length, unicode, injection strings 2. **Concurrency**: Race conditions, deadlocks, shared state 3. **Resource exhaustion**: Unbounded loops, memory leaks 4. **Type confusion**: Dynamic coercion, prototype pollution 5. **Security**: Path traversal, auth bypass, injection
Output
{
"verdict": "PASS" | "FAIL" | "NEEDS_IMPROVEMENT",
"vulnerabilities_found": [...],
"blocking_issues": [...]
}If verdict is FAIL, blocking_issues MUST be fixed.
Ships withnarsil-mcp
The blazing-fast, privacy-first MCP server for deep code intelligence A Rust-powered MCP (Model Context Protocol) server providing AI assistants with deep code understanding through 90 specialized tools.
Get the whole plugin
Stats
185
Stars
27
Forks
Active
Maintenance
Rust
Language
Apache-2.0
License
13d ago
Last commit
10mo ago
Created
5h ago
Added
Other agents on narsil-mcp.
Agent