Back to skill

Security audit

AllRatesToday

Security checks for vulnerabilities and agentic risk

Overview

The exchange-rate actions are read-only, but setup can execute changing remote code without verification or a clear approval step.

Review setup before enabling this skill. Install a verified CLI version yourself and require approval for subsequent installation changes. Review or disable its automatic skill synchronization using the controls in the [publisher command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). The sole bundled artifact was fully inspected; external installer behavior remains unverified. The Review verdict concerns setup control, not evidence of theft or destructive 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 only supplied command executes a remote installer, which is materially different from searching or reading AllRatesToday data. Nothing in the supplied chunk establishes that this installation is a supporting dependency of the declared functionality. The remote script's contents and any additional effects are not available for assessment.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The supplied chunk performs only a login operation; it does not search or read AllRatesToday data or identify an AllRatesToday resource. Authentication could support data access, but this chunk provides no evidence of that relationship, so its demonstrated purpose differs from the declared one.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

Piping the HTTPS installer directly into bash executes whatever content the endpoint returns without a separate verification or review step. HTTPS protects transport but does not prevent a compromised publisher or distribution system from delivering code that accesses local files, steals accessible credentials, or modifies the environment.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

Fallback setup executes remote installation scripts without warning about the system-integrity risk.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The fallback instructs the agent to execute remotely supplied shell or PowerShell code without an explicit approval checkpoint or integrity verification. A compromised installation endpoint or distribution pipeline could execute arbitrary code with the invoking user's permissions; limiting installation to missing-CLI failures reduces exposure but does not remove the risk.

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 71)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