ClawHub
Back to skill

Security audit

Photo Edit Analysis

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow photo critique prompt that does not install code, request credentials, persist data, or perform privileged actions.

Install this if you want direct editorial critique of photos, including letter grades. Be aware it may produce frank feedback when you ask about a photo's edit, exposure, or composition, especially if used with a photo-captioning workflow.

A.I.G

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

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
92% confidence
Finding

The README states the skill 'runs automatically alongside' another skill and also triggers on broad photo-related requests, but it does not define narrow activation boundaries. This can cause unintended invocation, leading the agent to analyze user images or requests when the user did not explicitly ask for this critique, which is a scope and privacy concern rather than direct code execution risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The sample trigger phrases are common conversational questions that could overlap with ordinary discussion of photos, making accidental activation more likely. In this skill's context, unintended invocation could expose user content to extra analysis or produce unsolicited judgments, which increases privacy and UX risk even though the skill itself is non-privileged.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.