ClawHub
Back to skill

Security audit

Backtesting

Security checks for vulnerabilities and agentic risk

Overview

This is a backtesting guidance skill with no executable code, persistence, credential handling, or hidden behavior found.

This skill appears safe to install as a backtesting reference. Because it can shape trading or deployment recommendations, users should still treat its output as analytical guidance rather than financial advice and verify any strategy with their own risk controls.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Whitespace Padding

Medium
Category
Prompt Injection
Confidence
70% confidence
Finding

Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Content

Scanner excerpt · SKILL.md (reported line 16)May include surrounding context.

md
Trade count is the single most important number on a result page. Look at it before PnL, before Sharpe, before win rate.

| Trade count | Verdict                                                                                  |
| ----------- | ---------------------------------------------------------------------------------------- |
| < 30        | **Coincidence, not a strategy.** Don't promise anything; widen entries or extend window. |
| 30-50       | Marginal. Sharpe is noisy. Treat results as directional, not numeric.                    |

Whitespace Padding

Medium
Category
Prompt Injection
Confidence
70% confidence
Finding

Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Content

Scanner excerpt · SKILL.md (reported line 93)May include surrounding context.

md
Each one tells a different story. Distortions diagnose specific bugs:

| Distortion              | Meaning                                                                                                                                        |
| ----------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- |
| 90% stoploss hits       | Stop is too tight relative to the strategy's natural noise. Widen, or accept this strategy is in the wrong volatility regime for this pair.    |
| 90% time-based timeouts | Exit signal does nothing. Either the exit conditions are too restrictive, or there's no real edge — you're just holding until the timer rings. |

Whitespace Padding

Medium
Category
Prompt Injection
Confidence
70% confidence
Finding

Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Content

Scanner excerpt · SKILL.md (reported line 98)May include surrounding context.

md
| 90% stoploss hits       | Stop is too tight relative to the strategy's natural noise. Widen, or accept this strategy is in the wrong volatility regime for this pair.    |
| 90% time-based timeouts | Exit signal does nothing. Either the exit conditions are too restrictive, or there's no real edge — you're just holding until the timer rings. |
| 100% take-profit hits   | `minimal_roi` is the strategy. The exit signal isn't earning its keep — could be removed or tightened.                                         |
| 50/50 stop vs profit    | Healthy. Strategy is choosing actively in both directions.                                                                                     |

## Zero-trade diagnosis

Static analysis

No suspicious patterns detected.