Back to skill

Security audit

undercurrent

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a benign verdict with no AIG findings and one concern about an unclear recurring activation condition; the review is incomplete because three referenced paths were not found.

Consider whether you want a skill with an unclear recurring activation trigger. The overall verdict is benign, but the scan was partial: three local path references were unresolved, so the evidence is incomplete.

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)

The activation condition “at every substantive wake” does not define which sessions or events qualify.

Medium
Category
Trigger Abuse
Confidence
90% confidence
Finding

“Substantive wake” is not defined, and the skill provides no exclusions or environment boundary for this recurring activation. This leaves the agent to decide whether unrelated conversations, scheduled runs, or routine tasks should trigger consultation and changes to its response style.

Content

No source excerpt is available for this finding.