Security audit

Content Scrubber

Security checks for vulnerabilities and agentic risk

Overview

The plugin appears defensive, but its redaction protection is narrower than advertised and could let internal infrastructure details pass through.

Review before relying on this as a privacy control. It does not appear malicious, but treat it as a best-effort scrubber: test your own sensitive formats, avoid dry-run mode for real protection, and do not assume it catches every internal hostname, SSH target, localhost form, or endpoint representation.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

Location: index.ts:15
Finding: Incomplete Redaction Rules Can Leak Private Infrastructure Details
Content: View full analysis
Remediation: View remediation

SkillSpector

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

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This manifest describes what the skill does, but it does not state when the skill should activate, what phrases or contexts invoke it, or any exclusions. For manifest files, missing trigger specificity can cause unintended invocation because there is no narrow scope or negative guidance.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.