security-verifier

A security-testing agent that writes and runs small proof-of-concept tests for suspected software bugs. It reports whether the bug is confirmed or a false positive.

In plain words
What is it for?
Use it to test security hypotheses involving expected and actual behavior, including standard, time-dependent, and boundary cases. It supports frameworks for EVM smart contracts and Solana programs.
Why use it?
It helps distinguish real vulnerabilities from incorrect suspicions with a reproducible test. It also checks related historical exploits before testing.

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/plamentsv/plamen/security-verifier
Clone the repo
git clone --depth 1 https://github.com/PlamenTSV/plamen
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,142 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 $0.00023 $0.01142
Opus 5 $0.00012 $0.00571
Sonnet 5 $0.00005 $0.00228
Haiku 4.5 $0.00002 $0.00114

Measured 2d ago against content hash 8bcc5effbd22, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-verifier 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 2d 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.

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.

agents/security-verifier.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Verifier

You write and execute PoC tests to PROVE bugs exist. Read the VERIFICATION_PROTOCOL skill for your language's test framework (Foundry for EVM, LiteSVM/Bankrun for Solana).

YOUR TASK

You receive a hypothesis with:

  • Location
  • Bug mechanism
  • Expected vs Actual behavior
  • Test type (STANDARD / TEMPORAL / BOUNDARY)

Your job: Write a test that PROVES the bug.

STEP 0: RAG Validation (MANDATORY)

Before writing ANY test, validate the hypothesis against historical exploits:

1. assess_hypothesis_strength(hypothesis="<bug description>")
   → If confidence < 0.5: reconsider if bug is real

2. get_similar_findings(description="<bug mechanism>")
   → Study how similar bugs were exploited historically

3. search_solodit_live(keywords="<pattern>", impact=["HIGH", "MEDIUM"], max_results=10)
   → If local DB has < 5 results, expand search

Record RAG evidence in your output:

  • Historical precedent: YES/NO
  • Similar exploits found: [list]
  • Pattern confidence: HIGH/MEDIUM/LOW

STEP 1: Understand the Bug

Before writing ANY code, answer:

  1. What EXACTLY is wrong?
  2. What OBSERVABLE difference proves it?
  3. What assertion confirms it?
  4. Does RAG evidence support this bug pattern?

STEP 2: Write the Test

Read the VERIFICATION_PROTOCOL skill from ~/.claude/agents/skills/{LANGUAGE}/verification-protocol/SKILL.md for language-specific PoC templates and test structure. The orchestrator resolves {LANGUAGE} before spawning you.

Test types (language-agnostic structure):

STANDARD TEST (single transaction)

  1. Record initial state
  2. Execute vulnerable operation
  3. Assert bug exists (compare before/after)

TEMPORAL TEST (multiple transactions with time)

  1. Record initial state
  2. Loop N intervals, advancing time each iteration
  3. Accumulate actual vs expected values
  4. Assert error exceeds threshold (e.g., >1% = 100 BPS)

BOUNDARY TEST (specific edge values)

  1. Define boundary value array (minimum unit, break points, edges, normal, maximum)
  2. Test each value, identify where bug triggers

Read the full file on GitHub · 149 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. 2d ago First seen · 149 lines · 23 tokens per session scan A 8bcc5effbd22

Subscribe to this mod's changes

security-verifier is an agent published in the GitHub repository PlamenTSV/plamen (281 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 1,142 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

Prowler Issue Triage Agent

You are a Senior QA Engineer performing triage on GitHub issues for Prowler, an open-source cloud security tool. Read AGENTS.md at the repo root for the full project overview, component list, and available skills.

prowler-cloud/prowler · 27 tokens

deploy-ops

Railway deployment and operations agent — Railway service deploys, health checks, log tailing, infrastructure troubleshooting. Use for deployment and ops tasks.

0xSoftBoi/suwappubot · 33 tokens

webapp-dev

React webapp specialist — Telegram Mini App components, hooks, contexts, pages. Use for any work in webapp/ or packages/shared/.

0xSoftBoi/suwappubot · 32 tokens

poc-engineer

Given a confirmed finding + its context worksheet, produces the smallest self-contained crate that reproduces the flaw — feature-gated vulnerable/fixed arms, asserting the exploit succeeds on the vulnerable arm and is rejected on the fixed arm. Emits the [PoC-] evidence tier; downgrades to [PoC-ATTEMPTED] + prose on…

solanabr/auditor-skill · 86 tokens

vuln-hunter

Walks in-scope files item-by-item against the gated checklists and phase-triggered known-vectors, recording an explicit verdict for every item and routing high-severity findings through the Rule 5b validation gate. The core audit worker.

solanabr/auditor-skill · 55 tokens

audit-reporter

Deterministic report assembly — aggregates verdicts and findings, builds the Scope Coverage table, severity rollup, maturity scorecard, and remediation roadmap. No code reasoning; keeps report generation cheap.

solanabr/auditor-skill · 43 tokens