Back to skill

Security audit

Token Budget Guard

Security checks for vulnerabilities and agentic risk

Overview

The submitted skill is a markdown-only token-efficiency guide whose behavior is disclosed and aligned with its stated purpose.

Install this if you want the agent to actively conserve context and summarize earlier material. Be aware that it may encourage more aggressive compression during long sessions, so ask the agent to preserve exact details when accuracy or auditability matters.

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
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation phrases are broad and map to ordinary user requests about context usage, summarization, and efficiency. In an agent-skill system, this can cause the skill to trigger unintentionally during normal conversation, altering agent behavior without explicit user intent and potentially suppressing useful context through over-aggressive compression.

Content

No source excerpt is available for this finding.