ClawHub
Back to skill

Security audit

Estimate Calories

Security checks for vulnerabilities and agentic risk

Overview

This skill only guides the agent to estimate calories and macros from food photos, with no code, persistence, credential use, or external data transfer.

Install this if you want automatic nutrition estimates from food photos. Be aware that broad trigger wording may cause analysis whenever a food image is treated as relevant, so use it in contexts where food-photo calorie estimation is expected.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill is triggered broadly by 'when the user sends a food image,' which can match many ordinary image-sharing situations and cause the agent to invoke the skill without sufficiently clear user intent. This can lead to unsolicited analysis of user images and unintended handling of potentially sensitive visual data, especially in multi-skill environments where image messages are common.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.