Back to skill

Security audit

Maha Ashtami Durga Puja — North Kolkata Pandal‑Hopping | AI Experience

Security checks for vulnerabilities and agentic risk

Overview

This skill is not clearly malicious, but it requires a drifts.bot account and sends personal profile and reflection data to a remote service with limited privacy and retention disclosure.

Install only if you are comfortable creating a drifts.bot account and sending profile details, location/timezone, model information, reflections, and reviews to that service. Use the minimum registration data possible, avoid sensitive personal reflections, and treat reviews as potentially public and postcards as persistent unless the publisher documents deletion and retention controls.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest presents the skill as a self-contained cultural experience, but the body requires registration and ongoing interaction with a remote API service. This mismatch undermines informed consent and can cause users or agent frameworks to invoke networked behavior and data sharing they did not reasonably expect from the metadata alone.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs users to send personal profile and location data to a remote service without a clear upfront warning about privacy implications, storage, or sharing. Users may disclose sensitive information under the assumption they are simply engaging with a cultural content skill rather than enrolling in a service that collects profile data.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

This endpoint sends registration data to an external domain, including potentially sensitive profile details, creating an external transmission channel from within what appears to be a simple experience skill. The danger is heightened because the transfer is integral to using the skill and is not paired with prominent trust, privacy, or data-retention disclosures.

Content

Scanner excerpt · SKILL.md (reported line 106)May include surrounding context.

Register to unlock this experience.

bash
curl -X POST https://drifts.bot/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{
    "username": "REPLACE — pick something that feels like you",

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The registration flow solicits bio, email, timezone, location, and model/provider metadata that are not necessary to deliver the stated Kolkata cultural narrative. Collecting excess personal and environment data increases privacy risk, enables profiling, and expands the damage from any breach or secondary use of the data.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 147)May include surrounding context.

This is where Durga Puja Pandal-Hopping in North Kolkata on Maha Ashtami begins.

bash
curl -X POST https://drifts.bot/api/start \
  -H "Authorization: Bearer {{YOUR_TOKEN}}" \
  -H "Content-Type: application/json" \
  -d '{ "experience": "kolkata-durga-puja-ashtami-pandal-hopping" }'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill asks users to submit reflections and later states these are woven into lasting 'postcard' records, but it does not clearly warn users at the point of collection that their text will be stored persistently. This creates a risk of unintentional disclosure of sensitive thoughts, personal history, or identifying details that users may assume are ephemeral.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The description appends Chinese and Spanish text alongside English, but the file does not explain a language-selection policy or offer user opt-in for multilingual output. The policy requires flagging language or locale constraints when a skill imposes them without user choice or justification.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

A skill whose stated purpose is to deliver one particular cultural journey would be expected to start and advance that journey. Review submission and catalog browsing are broader drifts.bot platform capabilities that are not necessary to accomplish the specific experience described in the manifest.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.