Back to skill

Security audit

Dry Clean Pickup Schedule

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only dry-cleaning pickup tracker with clear boundaries and no code, network, credential, payment, or account handling.

Installers should expect an English prompt-only assistant for organizing dry-cleaning pickup details. Avoid entering payment card data, account credentials, dispute evidence, or sensitive claims information; the skill itself instructs the agent not to handle those areas.

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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The checklist explicitly marks 'Language is English only,' and repeats that constraint in scan evidence. The policy provided says to flag language or locale restrictions unless the skill offers user choice or the constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The 'Clean Scan Evidence' section repeats that SKILL.md, skill.json, and ACCEPTANCE.md are 'English only.' This reinforces a language restriction that is not presented as optional and is not justified by any region-specific or compliance requirement.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file includes a natural-language statement that the skill is restricted to English only. Because this is a user-facing policy-style constraint rather than a region-specific compliance justification or user opt-in choice, it fits the language/locale policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest sets language: "en", which is a natural-language locale constraint. The file does not offer the user a language choice or explain why English-only behavior is necessary for this skill's function.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.