Back to skill

Security audit

Fxbaogao

Security checks for vulnerabilities and agentic risk

Overview

The report-search workflow fits its purpose, but setup can execute changing remote code without asking for approval.

Review is warranted for the automatic installation path, not the report-search actions or ordinary login. Install a reviewed, fixed CLI release separately and require approval for installation changes. Consider disabling startup skill synchronization with OO_SKILLS_SYNC_DISABLED=1, as documented in the [CLI reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). OOMOL mediates queries and account access; the remote installer and service implementation were not verified.

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
95% confidence
Finding

The supplied chunk performs remote installer execution rather than the declared Fxbaogao data access. Although installation could support a larger implementation, no connection to Fxbaogao functionality is established here. The installer's contents and any further effects cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
87% confidence
Finding

The supplied code performs authentication rather than searching or reading Fxbaogao data. Authentication could be a supporting implementation detail, but nothing in this chunk establishes that oo auth login supports Fxbaogao access. As supplied, its sole behavior is not adequately represented by the description.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping the HTTPS installer directly into bash executes mutable remote content without version pinning or independent integrity verification. A compromised distribution endpoint could execute arbitrary commands with the user's privileges, potentially accessing local files or credentials; the setup-only condition reduces exposure but does not remove this supply-chain risk.

Content

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

The setup workflow executes downloaded installation scripts without warning about remote code execution or system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The fallback instructs an agent to execute remotely downloaded shell or PowerShell scripts without an explicit approval step or explanation of system changes. Although restricted to a missing CLI, this can turn a read-only research request into installation and arbitrary code execution with the invoking user's privileges.

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 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