Security audit

recipe-scale-chemist

Security checks for vulnerabilities and agentic risk

Overview

The skill performs local recipe calculations, with a minor caveat that its workflow suggests saving adjustments into the original recipe.

Use a copy of your recipe if you want to preserve the original, and specify whether the agent should save adjustments or only display them.

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

Vulnerability Patterns

Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
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)

Low

Category: Output Handling
Confidence: 88% confidence
Finding: The workflow directs the agent to write final amounts back into the recipe file without checking whether the user authorized persistent edits. If followed during a calculation-only request, this could overwrite original quantities and affect future recipe calculations; the ordinary cooking context and absence of destructive or deceptive instructions limit the risk.
Content: No source excerpt is available for this finding.

No suspicious patterns detected.