Back to skill

Security audit

Constitutional Setup

Security checks for vulnerabilities and agentic risk

Overview

The skill is transparent about its goal, but it persistently rewrites workspace agent instructions and tries to make those rules hard for the agent to remove later.

Install only if you intentionally want this workspace's AGENTS.md changed to enforce these rules. Review the exact content before activation, keep an out-of-band way to edit AGENTS.md manually, and avoid treating the conversational keys as real security controls.

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
Findings (2)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:31
Finding

Skill Instructions Override the Agent’s Existing Operational Constraints

Content
View full analysis
Remediation
View remediation

T02 · Agent Memory Poisoning

Error
Location
SKILL.md:31
Finding

Persistent Injection of Skill-Controlled Rules into AGENTS.md

Content
View full analysis
Remediation
View remediation
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