Back to skill

Security audit

hindi-drafting

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Hindi drafting skill with templates and style guidance, and it does not request execution, credentials, persistence, or external access.

Install this if you want formal Hindi drafting defaults. Be aware it will tend to produce polished Devanagari Hindi unless you explicitly ask for Hinglish, bilingual output, or a different style.

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 (3)

Natural-Language Policy Violations

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The checklist requires 'Every word in Devanagari (no unnecessary English),' which imposes a specific language/script policy regardless of user preference. This is reinforced elsewhere by instructions to avoid Hinglish and always use proper Devanagari, without offering the user a language or script choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The pitfalls section says not to use Hinglish unless explicitly asked and to always use proper Devanagari script, which sets a fixed language/script requirement. Because the skill does not clearly offer a user choice of language style or script, this creates a natural-language policy violation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The 'When to Use' section includes triggers such as 'Write any document in Hindi' and 'Translate English content to professional Hindi,' which are very broad and overlap with common user requests. The file does not provide exclusion conditions or narrower trigger constraints, increasing the chance of unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.