CtrlK
BlogDocsLog inGet started
Tessl Logo

llm-trading-agent-security

Security patterns for autonomous trading agents with wallet or transaction authority. Covers prompt injection, spend limits, pre-send simulation, circuit breakers, MEV protection, and key handling.

64

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/llm-trading-agent-security/SKILL.md

The canonical home for this skill is tdg-personal/llm-trading-agent-security

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

The body is concise and highly actionable with executable code across all six security controls and a clear pre-deploy checklist, lacking only an explicit feedback-loop checkpoint for the risky send path.

Suggestions

Add an explicit simulate->validate->fix->re-simulate feedback loop in the 'Simulate before sending' section so failed simulations have a clear recovery path before any transaction is sent.

Number the layered-defense steps in 'How It Works' as an ordered sequence with a final verification checkpoint to strengthen workflow clarity for the high-risk execution flow.

DimensionReasoningScore

Conciseness

Lean prose with no explanation of concepts Claude already knows; the opening framing and section intros are tight and every code block earns its place.

3 / 3

Actionability

Six executable Python code blocks (injection regex guard, SpendLimitGuard, simulate-before-send, circuit breaker, wallet isolation, MEV config) are concrete and copy-paste ready.

3 / 3

Workflow Clarity

The 'How It Works' layered sequence and 'Pre-Deploy Checklist' provide structure, but for risky transaction-sending operations there is no explicit validate-fix-retry feedback loop, which caps workflow clarity at 2.

2 / 3

Progressive Disclosure

No bundle files are present; the single SKILL.md is organized into clear, well-signaled sections with no nested references, which for a self-contained skill satisfies the well-organized-sections anchor.

3 / 3

Total

11

/

12

Passed

Description

67%

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 clearly states what the skill covers with specific enumerated controls and a distinct niche, but it omits explicit 'Use when...' trigger guidance, which weakens completeness and trigger-term coverage.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g., 'Use when building or auditing a trading bot, on-chain execution assistant, or any agent that signs transactions').

Include common user-side phrasings like 'trading bot', 'crypto agent', or 'send transactions' alongside the technical terms to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Enumerates six concrete controls — 'prompt injection, spend limits, pre-send simulation, circuit breakers, MEV protection, and key handling' — matching the multiple-specific-actions anchor.

3 / 3

Completeness

The 'what' is clearly stated, but there is no explicit 'when'/'Use when' trigger guidance; per guideline a missing Use-when clause caps completeness at 2.

2 / 3

Trigger Term Quality

Domain terms like 'autonomous trading agents', 'wallet or transaction authority', and 'spend limits' are present, but it lacks natural user-side variations ('trading bot', 'crypto agent', 'send transactions') common phrasings users would say.

2 / 3

Distinctiveness Conflict Risk

The narrow scope of 'autonomous trading agents with wallet or transaction authority' carves a clear niche unlikely to conflict with unrelated skills.

3 / 3

Total

10

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
affaan-m/ECC
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.