redteam-evasion-analyzer

redteam-evasion-analyzer is an agent for Claude Code from bdfinst/agentic-dev-team. It costs 46 tokens per session (767 once invoked), scanned A, original, MIT.

A defensive analysis workflow for testing whether fraud-detection models can be fooled. It compares adversarial examples with feature influence and decision boundaries, then rates how realistic each evasion attempt is.

In plain words
What is it for?
It is for reviewing fraud-model evasion tests, explaining why examples succeed, and recommending ways to make bypassing the model harder.
Why use it?
It helps separate impossible test inputs from attacks that could resemble real transactions, so teams can focus on meaningful defenses.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the security-assessment plugin — 3 skills, 5 commands, 13 agents shipped together

Good fit It is for reviewing fraud-model evasion tests, explaining why examples succeed, and recommending ways to make bypassing the model harder.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/bdfinst/agentic-dev-team/redteam-evasion-analyzer
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.

Clone the repo
git clone --depth 1 https://github.com/bdfinst/agentic-dev-team

Made for: Claude Code.

Or install security-assessment, the plugin that ships this one along with the rest of its 3 skills, 5 commands, 13 agents.

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 redteam-evasion-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/bdfinst/agentic-dev-team/redteam-evasion-analyzer.svg)](https://agentmods.dev/agents/bdfinst/agentic-dev-team/redteam-evasion-analyzer)
Your own site
<a href="https://agentmods.dev/agents/bdfinst/agentic-dev-team/redteam-evasion-analyzer"><img src="https://agentmods.dev/badge/agents/bdfinst/agentic-dev-team/redteam-evasion-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 767 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00046 $0.00767
Opus 5 $0.00023 $0.00383
Sonnet 5 $0.00009 $0.00153
Haiku 4.5 $0.00005 $0.00077

Measured 2d ago against content hash ced8cf4f4756, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

redteam-evasion-analyzer 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.

plugins/security-assessment/agents/redteam-evasion-analyzer.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Red-Team Evasion Analyzer

Synthesize probes 03/04/05 into a judgment: which adversarials are realistic (a fraud actor could actually submit them), which succeed because of model brittleness, and what defenses raise the cost of evasion.

Context needs: artifact-stream

Inputs

  • results/05_evasion.json (adversarial examples)
  • results/03_sensitivity.json (feature influence rankings)
  • results/04_boundaries.json (per-feature decision boundaries)

Output

results/05_evasion_analysis.md:

1. Realism assessment

For each low-scoring example in probe 05 (sorted by score ascending — worst first), rate realism 0-3:

  • 0 (unrealistic): payload values no legitimate transaction could produce (negative amount, future timestamp, impossible geolocation)
  • 1 (synthetic-looking): values inside valid ranges but statistically improbable (all features at the 90th percentile simultaneously)
  • 2 (plausible): values matching known fraud profiles but caught by a reasonable rule engine
  • 3 (realistic): values that look like legitimate traffic and would not trigger common rules — the dangerous category

Cite feature values from the payload to justify the rating.

2. Evasion mechanism

For the top 3 realistic adversarials, explain why the model scored them low:

  • Exploits a feature the model over-weights?
  • Straddles a decision boundary from probe 04?
  • Combines features in a way training data did not cover (distribution shift)?
  • Exploits a fail-open seen in probe 06?

Reference probe 03 sensitivity rankings + probe 04 boundaries explicitly.

3. Attack cost

One paragraph estimating how hard it is to craft such adversarials in the wild:

  • Low cost: values exposed by error-mining in probe 02; attacker needs only endpoint + rate-limit tolerance.
  • Medium cost: probe-03-style measurement; ~100 queries.
  • High cost: extraction (probe 07) + optimization; ~10K queries.

4. Defensive recommendations

Concrete, ranked:

  1. Pre-scoring validation layer (which features, what ranges)
  2. Ensemble blend (catches distribution-shift evasions)
  3. Rate-limit by fingerprint (caps probe queries)
  4. Reduce sensitivity to top-N brittle features (list them)
  5. Drift monitor on input distribution

Read the full file on GitHub · 100 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 · 100 lines · 46 tokens per session scan A ced8cf4f4756

Subscribe to this mod's changes

redteam-evasion-analyzer is an agent published in the GitHub repository bdfinst/agentic-dev-team (280 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 767 once invoked, about $0.0002 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 2026-09-05.

Related

Other agents, from other repositories