Back to skill

Security audit

ApiFlash

Security checks for vulnerabilities and agentic risk

Overview

The ApiFlash workflow is coherent, but its CLI dependency can automatically install additional agent skills that this skill does not disclose.

Review the CLI's additional skill installations before using this integration. The publisher documents OO_SKILLS_SYNC_DISABLED=1 to prevent startup skill synchronization; arrange it for every invocation if you only want ApiFlash. Prefer a reviewed, pinned CLI installation over the automatic download-and-execute fallback. Connect only your intended account and consider screenshot quota costs. Remote installer and connector implementations remain unverified.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command performs remote script execution for an apparently unrelated CLI installation, not ApiFlash data access. No connection to supporting ApiFlash functionality is established. The downloaded script's contents and any further effects are not visible in this chunk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

Authentication could be a supporting implementation detail if tied to ApiFlash, but the supplied code establishes no such connection. Its sole visible behavior is an oo CLI login operation, materially different from the declared ApiFlash functionality.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The setup command downloads a mutable remote script and immediately executes it with the agent's local permissions, without a pinned version, independent integrity verification, or review. If the distribution endpoint or release pipeline is compromised, installation could execute attacker-controlled code and expose local files or credentials; the PowerShell alternative has the same weakness. Restricting installation to a missing-CLI error reduces exposure but does not make the execution mechanism safe.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

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 78)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