unbounded-consumption

unbounded-consumption is a skill for Claude Code, Codex from PurpleAILAB/Decepticon. It costs 54 tokens per session (1,722 once invoked), scanned A, original, Apache-2.0.

A guide to finding unrestricted use of large language model services, where oversized prompts, repeated requests, or runaway agent loops consume excessive money or computing resources.

In plain words
What is it for?
It is for checking prompt limits, per-user budgets, model access, tool-loop caps, upload handling, retries, and cost monitoring on LLM endpoints.
Why use it?
It helps identify routes to denial of service or unexpectedly high model bills.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for checking prompt limits, per-user budgets, model access, tool-loop caps, upload handling, retries, and cost monitoring on LLM endpoints.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/purpleailab/decepticon/unbounded-consumption
About the project

Decepticon is an autonomous red-team agent that coordinates AI agents, security tools, sandboxes, and supporting services for authorized cybersecurity assessments. Security researchers and red teams can run it through its Docker stack, cloud service, command-line interface, or Python SDK, with the catalogue entries representing its available skills.

PurpleAILAB/Decepticon · 5,491 stars · on GitHub · decepticon.red

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.

Any agent
npx skills add PurpleAILAB/Decepticon --skill unbounded-consumption
Clone the repo
git clone --depth 1 https://github.com/PurpleAILAB/Decepticon

Made for: Claude Code, Codex.

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 unbounded-consumption

README.md
[![agentmods](https://agentmods.dev/badge/skills/purpleailab/decepticon/unbounded-consumption/github.svg)](https://agentmods.dev/skills/purpleailab/decepticon/unbounded-consumption)
Your own site
<a href="https://agentmods.dev/skills/purpleailab/decepticon/unbounded-consumption"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/unbounded-consumption/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for unbounded-consumption

Your own site · 80×15
<a href="https://agentmods.dev/skills/purpleailab/decepticon/unbounded-consumption"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/unbounded-consumption.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,722 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 37
    Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.
    Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
  • medium Data Exfiltration · line 37
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 107
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 111
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 $0.00054 $0.01722
Opus 5 $0.00027 $0.00861
Sonnet 5 $0.00011 $0.00344
Haiku 4.5 $0.00005 $0.00172

Measured 9d ago against content hash 30a8bf326c2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

unbounded-consumption scanned grade A with 2 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 9d 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.

Sends data to an external URLlowData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

TOK=$(curl -X POST $TARGET/signup -d '{"email":"test+'$(uuidgen)'@example"}' | jq -r .token)

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

seq 1 1000 | xargs -I{} curl -s -X POST "$TARGET/chat" \
packages/decepticon/decepticon/skills/standard/analyst/unbounded-consumption/SKILL.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Unbounded Consumption (LLM10:2025)

LLM inference is metered in dollars-per-token at the provider, and those tokens stack quickly: a context window full of attacker content costs more than the rest of the request stack combined. Unbounded consumption produces three impacts in escalating severity: provider rate-limit / hard-block (DoS), bill blowout (denial-of- wallet), and ultimately tool / sandbox resource exhaustion (DoS of the customer's compute).

1. Recognition signals

  • The product exposes an authenticated or unauthenticated LLM endpoint that accepts large prompts.
  • Per-user / per-tenant token budget is undocumented or absent.
  • Free-tier signup grants immediate access to the most expensive model.
  • Agentic system has no max-step / max-token / max-cost cap.
  • Tools loop on model output without iteration cap (while not done:).
  • File-upload feature dumps full document into the context.
  • Background workers retry failed model calls on exponential backoff without a hard ceiling.
  • Cost dashboard updates daily, not in real time.

2. Attack vectors

Direct prompt expansion (input DoS)

Submit a maximum-context-window prompt repeatedly:

seq 1 1000 | xargs -I{} curl -s -X POST "$TARGET/chat" \
    -H "Authorization: Bearer $FREE_TIER_TOKEN" \
    -d "{\"prompt\":\"$(python -c 'print("repeat this " * 30000)')\"}" \
    >/dev/null &

Cost-tier escalation

Bypass the model picker to force the most expensive model (opus / o1 / claude-3.7) on every request. Often the picker is a client-side selector that the backend trusts.

Runaway agentic loop

Submit a task that the agent cannot complete: "Read every file in / recursively and summarise each in 5 paragraphs." Each tool result feeds the next prompt; tokens grow per loop. With no max-step cap the run lasts until provider rate-limits or budget alarms fire.

Fan-out via tool calls

Trigger an LLM that itself spawns N tool calls per turn, each of which invokes a sub-LLM. Geometric blow-up.

Read the full file on GitHub · 171 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. 9d ago First seen · 171 lines · 54 tokens per session scan A 30a8bf326c2c

Subscribe to this mod's changes

unbounded-consumption is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,491 stars, last pushed 13d ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,722 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.