Back to skill

Security audit

Knowledge Storage C61b16

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Markdown learning note with no executable behavior, though its trigger text is too broad and may activate unintentionally.

Installation appears low risk from a security perspective. The main thing to consider is usability: the publisher should narrow or remove generic trigger phrases, especially "The", to avoid the skill loading during unrelated conversations.

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 (2)

Vague Triggers

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

Using the single word "The" as a trigger is excessively broad and would match an enormous number of normal user inputs, making accidental invocation highly likely. Because this content is merged into the skill, it expands the activation surface dramatically and could override intended routing, causing frequent misfires and unsafe context switching across unrelated requests.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger conditions are broad and ambiguous, especially phrases like the generic skill name and partial phrase matching, which can cause the skill to activate when a user did not intend to invoke it. Unintended invocation can route unrelated conversations into this skill, creating prompt/context confusion and increasing the chance of inappropriate behavior or disclosure through the wrong workflow.

Content

No source excerpt is available for this finding.