Back to skill

Security audit

CraveGo Hashtag SEO Pack

Security checks for vulnerabilities and agentic risk

Overview

This skill only guides an agent to generate Philippines-focused hashtags and keyword phrases for CraveGo.ph marketing content.

Review generated hashtags for brand fit and factual accuracy before publishing, especially promo wording; the skill itself does not request sensitive access or perform actions on accounts.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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 (2)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 13)May include surrounding context.

md
Brand voice must be friendly & casual (but only in the example phrasing—hashtags themselves should be normal).

## Required output rules (to avoid thin/template outputs)
1) Generate a **mix** of:
   - broad food delivery hashtags (1/3)
   - Philippines/local intent hashtags (1/3)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The instruction says hashtags should be understandable to PH audiences and specifies that English or Taglish is fine. This imposes a language/locale preference in the skill behavior without indicating that the user can choose another language, which can violate language-choice policy requirements.

Content

No source excerpt is available for this finding.