Back to skill

Security audit

invariant-guarded-debugging

Security checks for vulnerabilities and agentic risk

Overview

This skill is a safety-oriented debugging checklist that asks the agent to verify constraints before making changes.

This skill is appropriate if you want a coding agent to slow down around risky fixes and prove protected behavior still works. Expect it to run or propose diagnostic checks before and after changes, and keep normal review for any privileged, destructive, or out-of-scope action it identifies.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 90)May include surrounding context.

md
User constraints and explicit contracts outrank derived requirements. Do not replace a protected boundary with an easier proxy and silently treat them as equivalent.

Protection is not limited to files. It may include:

- service state;
- API behaviour;