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.
npx skills add MingyiSecLab/Mingyi-Atlas --skill oracle-manipulationgit clone --depth 1 https://github.com/MingyiSecLab/Mingyi-AtlasWrote 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.
[](https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/oracle-manipulation)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/oracle-manipulation"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/oracle-manipulation/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.
<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/oracle-manipulation"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/oracle-manipulation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.01692 |
| Opus 5 | $0.00016 | $0.00846 |
| Sonnet 5 | $0.00007 | $0.00338 |
| Haiku 4.5 | $0.00003 | $0.00169 |
Grade A, and why
oracle-manipulation 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 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.
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.
This is a copy
92% identical to oracle-manipulation — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Oracle Manipulation Playbook
DeFi protocols that read a price from an on-chain source are vulnerable when the source can be moved within a single transaction or block. Classic vectors:
- Spot-price AMM oracle —
reserve1 / reserve0of a Uniswap V2 pool. Anyone with enough capital (or a flash loan) can push the price for one block. - Manipulable TWAP — short window TWAP, or TWAP over a low-liquidity pool.
- Single Chainlink feed without staleness check — feed returns 0 / stale → uses 0 in math.
- Custom oracle reading from manipulable storage — e.g., a "fair-price" oracle that reads
totalSupply()of an LP token alongside reserves. - L2 sequencer offline — L2 oracles need a "is sequencer up?" check or attacker can exploit when sequencer downs and feeds freeze.
Audit steps
1. Locate price-reading code
# Common patterns
grep -rn 'getReserves\|getAmountsOut\|getPriceFromSqrtPriceX96\|latestAnswer\|latestRoundData' src/
# Custom oracle reads
grep -rn 'IPriceOracle\|getPrice\|consult' src/
2. Trace each price use
For each call:
- Is the price read from a Uniswap V2 / Sushi / Camelot pool's reserves? → spot price = manipulable
- Is the price read from a Uniswap V3 pool's
slot0.sqrtPriceX96? → manipulable - Is it a Uniswap V3 TWAP via
OracleLibrary.consult? → check the secondsAgo window (>= 1800s = 30 min is the safe minimum) - Is it a Chainlink
latestRoundData()call? → check: isupdatedAtvalidated? IsansweredInRound >= roundId? Isanswer > 0? Are L2 sequencer feeds checked?
3. Validate staleness handling
// MISSING — vulnerable
(, int256 price, , , ) = priceFeed.latestRoundData();
// GOOD — explicit staleness + sequencer
(uint80 roundId, int256 price, , uint256 updatedAt, uint80 answeredInRound) = priceFeed.latestRoundData();
require(price > 0, "ORACLE_NEGATIVE");
require(updatedAt > block.timestamp - MAX_DELAY, "ORACLE_STALE");
require(answeredInRound >= roundId, "ORACLE_OLD_ROUND");
// On L2: also check sequencer uptime feed (L2 SequencerUptimeFeed)
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.
- 9d ago First seen · 153 lines · 33 tokens per session scan A 7b16e4c6b9b2
oracle-manipulation is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,692 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to oracle-manipulation, differing in 5 lines, and is treated as a copy.
Other skills, from other repositories
cis-aws-foundations-6.5
Ensure the default security group of every VPC restricts all traffic.
cis-aws-foundations-2.1.3
Ensure Organizations management account is not used for workloads.
cis-aws-foundations-2.12
Ensure access keys are rotated every 90 days or less.
cis-aws-foundations-2.5
Ensure MFA is enabled for the 'root' user account.
cis-aws-foundations-2.7
Eliminate use of the 'root' user for administrative and daily tasks.
cis-aws-foundations-4.4
Ensure that server access logging is enabled on the CloudTrail S3 bucket.