Back to skill

Security audit

Astrodai Vedic Astrology & Ephemeris

Security checks for vulnerabilities and agentic risk

Overview

The skill’s astrology calculations and optional purchase links fit its stated purpose, with privacy considerations when sharing birth details.

Use this skill only if comfortable sending birth details to Astrodai. Have the agent explain the transfer before the first calculation. Prefilled checkout links contain personal details, so avoid sharing them publicly. The complete scanner report and sole artifact were reviewed; the remote service implementation was not audited.

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)

The required remote calculation workflow lacks a user-facing disclosure that birth details will be sent to Astrodai.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The skill directs agents to use Astrodai's remote MCP tools with users' birth dates, exact birth times, and birthplaces without requiring a user-facing disclosure or consent before transmission. Although these details are relevant to the requested astrology service and the destination is openly identified in the skill, users may not realize their personal information will leave the agent environment; the stated privacy guarantees do not establish informed consent.

Content

No source excerpt is available for this finding.