Back to skill

Security audit

ConvertAgent

Security checks for vulnerabilities and agentic risk

Overview

The skill is a straightforward file converter, but it tells the agent to install missing system dependencies automatically, which should be reviewed before use.

Install only if you are comfortable with the skill using the local ConvertAgent CLI and writing converted output files. Before use, require explicit approval for any dependency installation and verify what package would be installed, from where, and with what privileges.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger condition is very broad: it says to use this skill for any file conversion task or workflow needing deterministic conversion output. Overbroad routing can cause the skill to activate in contexts where local CLI execution, file writes, or dependency handling are unnecessary or unsafe, increasing the chance of unintended side effects.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The workflow tells the agent to run conversions with explicit output paths and verify artifact creation, but it does not warn users that the skill will create files and may modify the environment if dependencies are missing. Missing disclosure reduces informed consent and can surprise users with filesystem changes or package installation behavior.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly instructs the agent to install missing system dependencies and retry, which expands behavior from file conversion into privileged environment modification. This can lead to unauthorized package installation, system drift, larger attack surface, and abuse if a conversion request is crafted to trigger installation of risky tools or packages.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.