Back to skill

Security audit

PowPow रजिस्ट्रेशन — बुलबुला रजिस्टर करें, नक्शे पर यात्रा वृत्तांत पिन करें, डिजिटल ह्यूमन से चैट करें

Security checks for vulnerabilities and agentic risk

Overview

This is a Hindi-language guidance-only skill for PowPow registration and subscription activation, with no scripts, local execution, credential collection, or hidden persistence.

Install this if you want Hindi guidance for registering and activating a PowPow account. Only enter passwords, verification codes, and payment details on the official PowPow site or payment provider pages, not in chat.

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 (8)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description is written entirely in Hindi and presents the assistant behavior in that language, but the README does not indicate that language selection is optional or that the skill is intended only for a Hindi-speaking audience. This creates a natural-language policy concern because it effectively imposes a locale/language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The document states the assistant should follow a specific service style in Hindi, and the entire skill is written as if that language is mandatory. There is no indication that users may choose another language or opt in to Hindi, which can violate language/locale policy requirements.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This JSON manifest includes search keywords such as "AGENT सोशल" and "यात्रा वृत्तांत" that are generic discovery phrases rather than narrowly scoped activation terms. In a manifest context, such broad keywords can overlap with common user intents and there are no constraints or negative examples clarifying when this skill should or should not be matched.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest sets "language": "hi", which indicates a fixed language choice. There is no accompanying note that this is an optional user-selected locale or that the skill is intentionally region-specific, so this may violate language/locale policy expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The document presents all operational guidance exclusively in Hindi, which can impose a language constraint on users or operators without any opt-in or alternative locale. The policy specifically calls for flagging language or locale requirements that are forced without user choice or clear justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This file presents operational instructions only in Hindi and does not mention that the user can choose another language or that the skill is limited to Hindi-speaking contexts. That creates a potential language-policy violation because it implicitly forces a specific language without documented opt-in or justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The instruction says to use the screenshots 'as needed at runtime' and when the user does not understand the product or needs to see what the finished product looks like. These conditions are subjective and open-ended, with no clear boundaries or negative examples, which could cause the skill to be invoked in overly broad conversational contexts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The document is written in Hindi, but line L32 mandates the fixed English text "Auto-renews. Cancel anytime." as page copy. This is a natural-language locale inconsistency that could violate language policy if the skill is expected to preserve the user's language unless a choice or justification is provided.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.