Security audit

fortune-telling(算命)

Security checks for vulnerabilities and agentic risk

Overview

This is a simple bilingual fortune-telling prompt skill that asks for a birth date and uses broad natural-language triggers, but it does not run code or access systems.

Install only if you are comfortable sharing a birth date for entertainment-style fortune readings. Treat outputs as non-advisory, especially for money, health, or major life decisions, and invoke the skill intentionally because some trigger phrases are broad.

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 (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The Chinese invocation examples use natural, generic phrasing like “算命，我是1990年5月15日出生的” and “帮我看看本周运势...”, which can overlap with ordinary conversation rather than an explicit skill invocation. If the platform routes on loose phrase matching, the skill may activate unintentionally and process sensitive personal data such as birth dates without clear user intent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The English examples, such as “Read my fortune” and “What's my weekly fortune?”, are broad requests that could easily appear in normal user conversation and are not clearly bound to this specific skill. In a permissive dispatcher, this ambiguity can cause unintended invocation, with the added privacy risk that users may disclose birthdays and personal information to the wrong handler.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The description explicitly states the skill is a '中英文' fortune-telling skill, which imposes a language/locale constraint in the manifest without any indication that users can choose their preferred language or opt in to that limitation. Under the policy, language constraints should either offer user choice or be clearly justified as region-specific.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.