Back to skill

Security audit

Weekly Meal Rhythm Planner

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only meal-planning skill with clear health boundaries and no executable code, network use, credentials, or persistence.

Safe to install if you want English-language, general meal-routine planning. Do not treat its output as medical nutrition advice, especially for allergies, eating disorders, pregnancy, diabetes, kidney disease, heart disease, or other medically restricted diets.

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
  • 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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The acceptance criteria explicitly require 'English only' and repeat 'English-only content' in the scan evidence. This is a natural-language locale restriction, and the file does not indicate user choice, opt-in, or a justified region-specific need.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest lists triggerKeywords such as "routine," "food," and "weekly planning," which are generic phrases that could match many unrelated conversations. The file does not provide exclusion conditions or negative examples to clarify when the skill should not activate.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest lists generic trigger keywords such as "routine" and "food," which overlap with common everyday language and do not narrowly identify this specific meal-planning skill. The file also does not provide exclusion conditions or tighter scope constraints to reduce accidental activation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
73% confidence
Finding

The manifest sets language to "en," which can be interpreted as forcing a specific language or locale. The file does not mention any user language choice, opt-in, or justification for an English-only constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The manifest specifies "language": "en", which can represent a language restriction without any accompanying user opt-in, multilingual option, or justification for why the skill must be English-only. Under the policy, language constraints should either be optional for users or clearly documented as necessary.

Content

No source excerpt is available for this finding.