Back to skill

Security audit

Strategy Advisor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain Markdown strategy-advice prompt with an Evvo strategy reference, and it does not run code, install anything, persist changes, or request outside access.

Install this only in contexts where Evvo Labs internal strategy material is appropriate for the agent to read and use. The main practical risk is accidental use of the bundled strategy context in broader Evvo business conversations, not malware-like behavior.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The invocation description is broad enough to match a wide range of ordinary business and opinion-seeking prompts, which can cause the skill to activate outside narrowly intended scenarios. Over-broad routing increases the chance that unrelated requests are steered into this skill's prescribed behavior and context, creating mis-scoping, policy bypass of more appropriate skills, or unintended disclosure/use of internal strategic context.

Static analysis

No suspicious patterns detected.