Back to skill

Security audit

Foursquare

Security checks for vulnerabilities and agentic risk

Overview

The Foursquare features are coherent, but setup executes unverified downloaded code without clearly scoped user approval.

Review and install the CLI separately before enabling this skill, checking its bundled-skill synchronization settings and local changes. The external installer and exact downloaded release were not verified. Use only location and search information you intend to share through OOMOL with Foursquare. No artifact evidence establishes malicious intent.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied chunk performs remote installer execution, not Foursquare data access. Nothing in the chunk establishes that this installation is a supporting dependency for the declared functionality. The downloaded script's contents are unavailable, so its further behavior cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

The command pipes a mutable remote response directly into Bash, allowing that response to run arbitrary code with the invoking user's permissions. HTTPS protects transport but does not protect against compromise of the publisher or distribution infrastructure; this is the same underlying installation risk identified in the setup finding, not an additional independent vulnerability.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

Read actions are labeled safe without warning that location and search inputs are sent to external services.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The workflow instructs the agent to execute connector actions with input payloads, including latitude and longitude for nearby-place lookups. Although OOMOL and Foursquare are identified, the skill does not warn that these inputs can disclose sensitive user location or search information to those services; labeling reads as safe overlooks that privacy impact.

Content

No source excerpt is available for this finding.

Setup instructs immediate execution of downloaded installation scripts without a system-integrity warning.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

Both setup examples execute remotely downloaded scripts immediately, without an inspection step, pinned version, or independently verified integrity. A compromised distribution endpoint or malicious installer update could execute arbitrary commands with the invoking user's privileges; limiting setup to a missing-CLI error reduces exposure but does not eliminate it.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 80)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources