Back to skill

Security audit

Pagrehistro ng PowPow — magrehistro ng Bula, i-pin ang talaarawan ng paglalakbay sa mapa, kausapin ang digital na tao

Security checks for vulnerabilities and agentic risk

Overview

This is a guide-only registration helper that stays scoped to explaining PowPow signup, screenshots, errors, and subscription steps without collecting credentials or running code.

Install this if you want a Tagalog guide for PowPow registration and subscription activation. Users should still complete signup and payment only on the official PowPow pages and should not share passwords, verification codes, or payment credentials 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 (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The README is entirely written in Filipino and does not indicate that other languages are supported or that the language restriction is intentional for a region-specific audience. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The notes field contains Chinese text while the file declares "language": "tl", creating a language inconsistency in natural-language metadata. This can violate language/locale policy because the skill content appears to force or assume a language different from the declared locale without user opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file contains end-user guidance entirely in a specific language context, but it does not indicate that the user opted into Filipino or that the skill is region-specific. Under the policy, forcing a specific language or locale without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

This markdown file includes a table of 'original error text in Mandarin' and repeated Mandarin-only messages users will encounter during registration and login. Under the policy, forcing a specific language without opt-in can be a natural-language policy concern when no alternative language option or regional justification is stated.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The instruction says to send a screenshot when the user has 'no concept' of Bubble or when it is necessary to 'see' the finished product, but it does not define clear boundaries for when that condition is met. This leaves activation to broad subjective judgment and could lead to screenshots being sent in situations beyond the intended scope.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The per-image usage guidance provides sample situations, but the trigger scope remains open-ended because it does not specify whether these are exhaustive or merely illustrative. Without negative examples or constraints, the skill may invoke screenshot sharing based on broadly similar everyday phrasing.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.