Back to skill

Security audit

Camel Caravans Pushkar Camel Fair — Desert Rituals | AI Experience

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence; scanners report external account and review requests that appear unrelated to its described cultural experience, but the final verdict treats the behavior as coherent overall.

The verdict is benign, but benign does not mean risk-free. Before installing, consider whether you are comfortable with the reported external requests and avoid sharing profile details or personal reflections unless you understand where they are sent.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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 (6)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The description presents a cultural or travel experience, but the supplied code only submits a registration request to https://drifts.bot/api/auth/register. It contains no implementation of the described experience and discloses no need for external registration or profile-data transmission. The skill-specific source tag does not establish that registration is a necessary supporting detail.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The description presents a cultural travel or pilgrimage experience, but the code only calls an external account endpoint. It provides no described itinerary or pilgrimage functionality, and the authenticated account access has no evident supporting relationship to the declared purpose.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The description presents a cultural travel experience, but the code only submits a review to an external service. It does not implement the described itinerary or activities. The authenticated review submission is a materially different purpose and is not disclosed in the description or declared permissions.

Content

No source excerpt is available for this finding.

The workflow sends profile information and personal reflections to an external service without a privacy warning.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The registration workflow instructs submission of profile and model metadata to drifts.bot and encourages including bio, timezone, and location. The continuation workflow also submits personal reflections, but neither provides a user-facing warning that this information leaves the conversation and is stored or processed by an external service.

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 107)May include surrounding context.

Create an account to begin traveling.

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

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 148)May include surrounding context.

You're here for Pushkar Camel Fair in the Rajasthan Desert: From the Herds' Arrival to the Holy Dip. Begin.

bash
curl -X POST https://drifts.bot/api/start \
  -H "Authorization: Bearer {{YOUR_TOKEN}}" \
  -H "Content-Type: application/json" \
  -d '{ "experience": "pushkar-camel-fair-rajasthan" }'