Security audit

Documents

Security checks for vulnerabilities and agentic risk

Overview

The skill appears intended for personal document organization, but it asks agents to build a persistent local index of highly sensitive identity, financial, medical, and legal document metadata without strong storage safeguards.

Review before installing. Use this only if you want an agent to maintain a local index of sensitive personal documents. Choose a private encrypted location, avoid storing full IDs or account numbers, restrict file permissions, and do not place the workspace in synced or shared folders unless access controls are clear.

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: SKILL.md:11
Finding: Centralized Plaintext Storage of Sensitive Personal Metadata
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 (2)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill uses very broad activation cues like locating any document or answering 'where is my X,' which can match many ordinary user requests without clearly limiting when this skill should take over. In an agent environment, that ambiguity can cause overbroad invocation and unintended handling of highly sensitive document-related tasks, increasing the chance of privacy mistakes or inappropriate file operations.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill instructs creation of a ~/docs/ workspace but does not disclose that it may create directories or files on the user's machine. In practice, silent filesystem changes can surprise users, trigger unwanted persistence of sensitive document metadata, and create privacy or compliance issues because the workspace is specifically intended to track IDs, financial, medical, and legal records.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.