Back to skill

Security audit

Briefing Note

Security checks for vulnerabilities and agentic risk

Overview

This is a simple briefing-note writing skill with no code, persistence, or hidden access; its only notable issue is a somewhat broad activation phrase.

This appears safe to install for drafting formal briefing notes. Be aware that it may activate for some decision- or meeting-related summary requests, and users should still verify facts, sensitivities, and recommendations before relying on the output.

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
90% confidence
Finding

The manifest description says to use the skill when asked to "summarize an issue for a decision or meeting," which is a broad natural-language trigger that can overlap with everyday summarization requests. The file does not provide explicit trigger boundaries, exclusion conditions, or negative examples to clarify when this skill should activate instead of a general summarization workflow.

Content

No source excerpt is available for this finding.