ClawHub
Back to skill

Security audit

Zodiac Horoscope

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its horoscope purpose, but it asks for sensitive personal data and allows an agent to retrieve email verification codes, which is broader access than the feature needs.

Install only if you are comfortable sending your email, birth date, and birth city to zodiac-today.com and storing an API key/profile ID for later use. Do not give the agent mailbox or IMAP access for verification codes; manually read and enter any code yourself, and treat the horoscope output as entertainment or reflection rather than a basis for major financial, employment, health, safety, or legal decisions.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill is positioned to give actionable advice for interviews, travel, romance, purchases, and important decisions based on horoscope output, without clear cautionary boundaries. In context, this can materially influence consequential user decisions using non-evidence-based signals, creating risk of harmful guidance and overreliance, especially when presented as optimization advice.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrases are broad enough to match ordinary planning or advice-seeking requests such as 'what should I do today' or 'best day to,' which can cause the skill to activate outside a clearly astrology-specific context. That increases the chance users are routed into a workflow that collects sensitive PII and provides horoscope-based guidance when they did not intend to use such a service.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 51)May include surrounding context.

bash
# Send verification code (creates account if new)
curl -s -X POST https://zodiac-today.com/api/auth/send-code \
  -H "Content-Type: application/json" \
  -d '{"email":"user@example.com"}'

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly authorizes automatic retrieval of a 6-digit verification code from the user's email account via IMAP, which expands access far beyond what is needed to provide horoscope functionality. Granting an agent mailbox access to intercept authentication codes creates a powerful account-compromise primitive and could expose unrelated emails, tokens, and personal data if misused or over-scoped.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The documentation says 'no browser needed' and frames setup as straightforward API use, but later introduces optional access to the user's email account to retrieve verification codes. This omission is security-relevant because it downplays a materially more sensitive permission requirement, reducing informed consent and increasing the chance an agent is granted unnecessary access.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.