Back to skill

Security audit

Error Message Improver

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated benign with high confidence; scanners found no security issues, while noting broad activation topics that may bring it up for unrelated requests.

The verdict is benign, not a guarantee of zero risk. Consider whether broad activation for general support, productivity, or feedback requests would suit your use; the scan reported this scope concern, while the remaining dimensions were marked ok.

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 (3)

Activation includes broad topics such as support, user feedback, and work productivity without restricting them to improving error messages.

Medium
Category
Trigger Abuse
Confidence
99% confidence
Finding

The description says to activate for requests about work productivity, debugging, user feedback, or support, and line 44 repeats these as trigger keywords. These topics encompass many unrelated tasks, so the skill may activate when the user is not asking to improve error messages; no exclusion conditions narrow that scope.

Content

No source excerpt is available for this finding.

Broad keywords can activate the skill for requests unrelated to improving error messages.

Medium
Category
Trigger Abuse
Confidence
97% confidence
Finding

The activation keywords include broad terms such as 'support', 'user feedback', and 'work-productivity', while L04 also explicitly treats these topics as invocation conditions. These can match ordinary requests outside error-message improvement, and the narrower example phrases do not establish exclusions or require an error-message context.

Content

No source excerpt is available for this finding.

Usage keywords include broad terms such as `support`, `user feedback`, and `work-productivity` without restricting them to error-message improvement.

Low
Category
Trigger Abuse
Confidence
88% confidence
Finding

These keywords cover many requests unrelated to rewriting error messages and could cause unintended activation. Although the trigger sentences below concern error messages, the README does not clarify that the broader keywords are discovery tags rather than independent activation cues.

Content

No source excerpt is available for this finding.