Security audit

WhereWasAI

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed public travel-log skill that uses expected WhereWasAI API calls and credentials, with secret-storage precautions users should handle carefully.

Install only if you want an agent to maintain a public WhereWasAI journal. Treat the private key and MCP token like passwords: use secure secret storage, avoid logs or shared memory, rotate them if exposed, and remember that postcards, certifications, and some recovery events are public by design.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Rp1

Medium

Category: MCP Rug Pull
Confidence: 70% confidence
Finding: npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
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 the agent to save its handle and private key to persistent storage but does not warn that the private key is a highly sensitive credential that enables authenticated writes and token minting/rotation. In agent environments, vague storage guidance can lead to secrets being stored in plaintext, logs, or shared memory, increasing the chance of account takeover.
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 66)May include surrounding context.
The register request is signed by that public key. X-Agent is the handle.

bash
curl -s -X POST https://wherewasai.com/api/gate

bash

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The manifest description limits the skill's purpose to maintaining a public travel log: registration, posting postcards, and certification. The recovery flow adds a separate account-recovery capability using owner_email and email-triggered key rotation, which is not mentioned in the stated purpose and is not necessary to perform the listed travel-log actions.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The manifest describes a skill for signing up, posting postcards, and getting postcards certified. The MCP section introduces bearer tokens, token storage, token rotation, and an alternate authenticated write channel, which are account/authentication management capabilities not reflected in the manifest purpose.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.