Security audit

PowPow नोंदणी — बुडबुडा नोंदणी करा, प्रवासवर्णन नकाशावर पिन करा, डिजिटल ह्युमनशी चॅट करा

Security checks for vulnerabilities and agentic risk

Overview

This is a guide-only Marathi skill for PowPow account registration and subscription activation, with no scripts or hidden high-risk behavior found.

Before installing, confirm you want Marathi-language PowPow registration guidance and only enter passwords, verification codes, and payment details directly on the official PowPow or payment-provider pages, not in chat.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
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 (7)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High

Category: YARA Match
Confidence: 80% confidence
Finding: YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).
Content: Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.
md
--- name: powpow-register description: वापरकर्त्याला PowPow (बबल) खाते नोंदणी करण्यास आणि सबस्क्रिप्शन अॅक्टिव्हेट करण्यास मदत करते. जेव्हा वापरकर्ता म्हणतो «बबल नोंदणी करा» «PowPow खाते नोंदणी करा» «बबलची नोंदणी कशी करायची» «माझ्यासाठी एक PowPow खाते नोंदणी करा» «sign up powpow» ते�

Hidden Instructions

High

Category: Prompt Injection
Confidence: 60% confidence
Finding: Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
Content: Scanner excerpt · SKILL.md (reported line 20)May include surrounding context.
md
## रनिंग एन्व्हायर्नमेंट हे skill पूर्णपणे **मार्गदर्शक-प्रकारचे** आहे: त्यात कोणतीही स्क्रिप्ट नाही, Node किंवा इतर कोणत्याही डिपेंडन्सीची गरज नाही. सर्व कृती (फॉर्म भरणे, व्हेरिफिकेशन कोड घेणे, पेमेंट) वापरकर्ता स्वतः ब्राउझर/अ‍ॅपमध्ये पूर्ण करतो, तुम्ही फक्त परिचय करून देता, मार्ग दाखवता आणि समस्येचे निराकरण करता. ## Trigger Conditions

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The description and operating instructions are written as if the skill should interact in Marathi, but there is no indication that the user can choose another language or opt in to this locale constraint. The policy calls for flagging language or locale constraints that are forced without user choice or documented justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest explicitly sets the skill language to "mr" on L14, while other visible text in the file includes Chinese and Marathi, suggesting a fixed locale choice rather than user-selected language behavior. The policy requires avoiding forced language or locale constraints unless the skill offers opt-in or clearly documents a justified regional limitation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 80% confidence
Finding: The entire skill reference is written in Marathi and does not mention any option for using another language or locale. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy concern unless the locale restriction is explicitly justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The entire skill file is written in Marathi, while embedded error strings and product references indicate a multilingual context. There is no natural-language statement offering alternative languages or explaining that the skill is intentionally limited to Marathi users, which can violate language/locale policy requirements.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The document’s operational instructions and usage guidance are fully expressed in Marathi, with no indication that the user may choose another language or that the skill is limited to a Marathi-speaking context. This creates a natural-language locale constraint that can violate organizational language-choice policy.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.