Security audit

Screenshot Capture

Security checks for vulnerabilities and agentic risk

Overview

This skill has a coherent personal screenshot-saving purpose, but it can automatically preserve shared images, edit notes, and create reminders from broad triggers without clear pre-action confirmation.

Install only if you want screenshots shared in matching contexts to be automatically saved into local notes, summarized, pattern-logged, and paired with reminders. Avoid using it for sensitive screenshots unless you first narrow the trigger, require confirmation before writes, and ensure file paths are handled safely with sanitized names and structured file operations.

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:10
Finding: Unquoted File Paths May Enable Shell Command or Option Injection
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 (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill description is broad enough to trigger on ordinary screenshot-sharing behavior such as sending an image with casual context like 'save this.' That increases the chance the agent will activate without clear user intent and then perform side effects such as storing files and modifying notes, which can lead to unauthorized persistence of sensitive content.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The workflow says 'When Enzo shares a screenshot with comments, execute this workflow' without requiring confirmation, scoping rules, or exceptions. Because the workflow includes copying files, editing multiple notes, and setting reminders, underspecified triggering can cause unintended actions and durable changes from ambiguous conversational input.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill automatically copies inbound images, updates several files, logs patterns, and always creates a reminder, but this behavior is not clearly disclosed up front. Hidden or insufficiently signaled side effects are dangerous because users may share screenshots expecting analysis only, while the agent silently persists possibly sensitive content and creates additional records and tasks.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.