CtrlK
BlogDocsLog inGet started
Tessl Logo

flash-loan

Flash-loan exploit patterns — callback reentrancy, oracle amplification, governance attacks, unauthenticated callback handlers.

64

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/contracts/flash-loan/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The playbook is highly actionable with executable Solidity/Foundry examples and a clearly sequenced audit workflow, well-organized into focused sections. Minor room to tighten framing prose and make the audit validation feedback loop explicit.

DimensionReasoningScore

Conciseness

The body is lean and assumes Solidity/DeFi competence (one-line framing, terse source list, focused code blocks), but contains minor explanatory asides like "They're not vulnerabilities themselves — they're a force multiplier" and the parenthetical ERC4626/reentrancy note that could be trimmed — the efficient 4 rather than the every-token-earns-its-place 5.

4 / 5

Actionability

Provides copy-paste-ready Solidity snippets for each pattern, an executable grep one-liner, a concrete Foundry PoC template with real Aave V3 pool address and assertGt check, and an explicit foundry_inflation_test(...) tool call — fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

The 'Audit steps' are clearly sequenced (locate integrations → per-handler checks → price-reading functions → share-mint/burn with a Foundry validation test) with concrete sub-checks, but the feedback loop (fail → fix → re-validate) is implicit rather than an explicit checkpoint — the 4 anchor with minor validation gaps.

4 / 5

Progressive Disclosure

Well-organized into clear single-purpose sections (attack patterns, audit steps, severity, PoC, OPSEC, remediation, exemplars) with clearly signaled one-level-deep cross-references to sibling skills (oracle-manipulation/SKILL.md, reentrancy/); no bundle files exist, and sections like Known exemplars/PoC template could arguably split into references, so 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and well-targeted, naming a clear niche plus four concrete attack patterns with supporting trigger keywords in metadata. It would benefit from an explicit 'Use when...' clause with protocol-name triggers directly in the description field.

DimensionReasoningScore

Specificity

Names the domain ("Flash-loan exploit patterns") and lists four concrete sub-patterns ("callback reentrancy, oracle amplification, governance attacks, unauthenticated callback handlers"), matching the 'lists several specific actions; minor gaps' anchor rather than the fully comprehensive 5.

4 / 5

Completeness

The 'what' is explicit (exploit patterns and four concrete types) and an equivalent explicit trigger guidance exists via metadata.when_to_use ("flash loan aave dydx balancer composition"), so it clears the 3-cap; the 'when' is terse keyword-only rather than a concrete 'Use when...' clause, fitting the 4 anchor.

4 / 5

Trigger Term Quality

"Flash-loan" plus the named attack types are natural terms a security auditor would say, and metadata.when_to_use adds "aave dydx balancer"; good coverage but a few natural synonyms/protocol names are absent from the description field itself, so 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

"Flash-loan exploit patterns" is a clear niche with distinct triggers, but the body explicitly cross-references sibling skills (oracle-manipulation, reentrancy), indicating minor overlap risk with closely related skills — the 4 anchor rather than the minimal-conflict 5.

4 / 5

Total

16

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

relative_links

Relative link issues: 3 missing

Warning

Total

13

/

16

Passed

Repository
PurpleAILAB/Decepticon
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.