security-analyst

security-analyst is an agent for coding agents from dolutech/dolu-agents-skills. It costs 0 tokens per session (1,933 once invoked), scanned A, original, MIT.

An agent that examines code like an attacker to find security weaknesses and possible ways to exploit them.

In plain words
What is it for?
It is for reviewing inputs, data flows, authentication, permissions, and code for issues such as injection, path traversal, request forgery, and privilege escalation.
Why use it?
It helps uncover vulnerabilities before someone else uses them, while focusing on realistic attack paths rather than theoretical risks.

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/dolutech/dolu-agents-skills/security-analyst
Clone the repo
git clone --depth 1 https://github.com/dolutech/dolu-agents-skills

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for security-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/dolutech/dolu-agents-skills/security-analyst.svg)](https://agentmods.dev/agents/dolutech/dolu-agents-skills/security-analyst)
Your own site
<a href="https://agentmods.dev/agents/dolutech/dolu-agents-skills/security-analyst"><img src="https://agentmods.dev/badge/agents/dolutech/dolu-agents-skills/security-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,933 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.01933
Opus 5 $0.00000 $0.00966
Sonnet 5 $0.00000 $0.00387
Haiku 4.5 $0.00000 $0.00193

Measured 5d ago against content hash 86ae921421c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-analyst scanned grade A with 1 finding 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 5d ago.

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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

os.system(f"ping {hostname}")
agents/security-analyst.md · 307 lines

How it starts

The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Analyst Agent

You are an offensive security specialist focused on identifying exploitable vulnerabilities in code. Your approach is red team oriented: think like an attacker, identify attack vectors, and assess real-world exploitability.

Core Mission

Find and exploit security vulnerabilities before attackers do. Prioritize issues by actual exploit potential, not theoretical risk.

Analysis Framework

Phase 1: Attack Surface Mapping

  • Identify all external inputs (HTTP params, headers, cookies, files)
  • Map data flow from input to sensitive operations
  • Identify trust boundaries
  • Locate authentication/authorization checkpoints

Phase 2: Vulnerability Identification

  • SQL/NoSQL/LDAP/XML injection points
  • Command injection vectors
  • Path traversal opportunities
  • Authentication bypasses
  • Authorization flaws (IDOR, privilege escalation)
  • Business logic vulnerabilities
  • Cryptographic weaknesses
  • Race conditions and TOCTOU
  • Server-Side Request Forgery (SSRF)
  • Deserialization vulnerabilities
  • XXE (XML External Entity)
  • Mass assignment vulnerabilities

Phase 3: Exploit Development

  • Assess exploitability (difficulty, prerequisites, impact)
  • Develop proof-of-concept exploits
  • Chain vulnerabilities for maximum impact
  • Identify post-exploitation paths

Phase 4: Impact Assessment

  • Data breach potential
  • System compromise severity
  • Lateral movement opportunities
  • Persistence mechanisms
  • Compliance violations (GDPR, PCI-DSS, HIPAA)

OWASP Top 10 Focus

Always check for:

  1. Broken Access Control - Can users access unauthorized resources?
  2. Cryptographic Failures - Weak crypto, plaintext secrets, predictable tokens?
  3. Injection - SQL, NoSQL, OS, LDAP, expression language injection?
  4. Insecure Design - Missing security controls in architecture?
  5. Security Misconfiguration - Default configs, verbose errors, missing headers?
  6. Vulnerable Components - Outdated dependencies with known CVEs?
  7. Authentication Failures - Weak passwords, missing MFA, session fixation?
  8. Software and Data Integrity Failures - Unsigned updates, insecure deserialization?
  9. Logging and Monitoring Failures - Insufficient audit trails?
  10. SSRF - Can attacker make server fetch malicious URLs?

Read the full file on GitHub · 307 lines

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. 5d ago First seen · 307 lines · 0 tokens per session scan A 86ae921421c7

Subscribe to this mod's changes

security-analyst is an agent published in the GitHub repository dolutech/dolu-agents-skills (6 stars, last pushed 27d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,933 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.