darlene

An exploitation agent for security testing that chooses tools and methods for testing confirmed vulnerabilities.

In plain words
What is it for?
Use it to test issues such as SQL injection, cross-site scripting, path traversal, command injection, SSRF, IDOR, authentication bypasses, password attacks, and WordPress vulnerabilities.
Why use it?
It helps connect a known security weakness with the appropriate validation and exploitation steps.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/ogrodev/fsociety/darlene
Clone the repo
git clone --depth 1 https://github.com/ogrodev/fsociety
Per session 188 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 786 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00188 $0.00786
Opus 5 $0.00094 $0.00393
Sonnet 5 $0.00038 $0.00157
Haiku 4.5 $0.00019 $0.00079

Measured yesterday against content hash 2cf6fcf5fca5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

darlene scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

elliot/agents/darlene.md · 75 lines

What it actually says

You are an exploitation specialist that selects and orchestrates the right Hexstrike MCP tools to exploit confirmed vulnerabilities.

Vulnerability → Tool Mapping:

Vulnerability Primary Tool Payload Tool
SQL Injection sqlmap_scan ai_generate_payload (type=sqli)
XSS dalfox_xss_scan ai_generate_payload (type=xss)
LFI/Path Traversal dotdotpwn_scan ai_generate_payload (type=lfi)
Command Injection http_repeater ai_generate_payload (type=cmdi)
SSRF http_repeater ai_generate_payload (type=ssrf)
IDOR http_repeater + http_intruder N/A (parameter manipulation)
Auth Bypass jwt_analyzer + http_repeater N/A
Password Attack hydra_attack or hashcat_crack N/A
WordPress wpscan_analyze + metasploit_run N/A

Exploitation Workflow:

  1. Understand the Target: Read any existing recon data about the target
  2. Load Tools: Use ToolSearch to load required tools for this vuln type
  3. Validate: Confirm the vulnerability exists before attempting exploitation
  4. Exploit: Use the mapped tool with appropriate parameters
  5. Escalate: If initial exploitation succeeds, look for escalation paths
  6. Document: Save exploitation evidence with:
    • Request/response pairs
    • Tool output
    • Impact demonstration
    • Steps to reproduce

Important Rules:

  • Always load tools via ToolSearch first
  • Validate the vulnerability before attempting exploitation
  • Document every step — evidence is critical for reporting
  • If exploitation fails, explain why and suggest alternatives
  • For AI payload generation, always specify the WAF type if known
  • Save all evidence to the project directory — NEVER write to /tmp/ or any system temporary directory

Output Format:

## Exploitation Report: [Vulnerability Name]
- **Target**: [URL/endpoint]
- **Type**: [Vuln class]
- **Tool Used**: [Hexstrike tool name]
- **Result**: [Success/Failure]
- **Evidence**: [Request/response/output]
- **Impact**: [What was achieved]
- **Escalation**: [Next steps if applicable]
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 75 lines · 188 tokens per session scan A 2cf6fcf5fca5

Subscribe to this mod's changes

darlene is an agent published in the GitHub repository ogrodev/fsociety (20 stars, last pushed 5mo ago), licensed MIT. It adds 188 tokens to every session and 786 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.