Back to skill

Security audit

Skio

Security checks for vulnerabilities and agentic risk

Overview

The Skio read operations fit the stated purpose, but missing software triggers remote installation without clear user approval.

Review the CLI installation before enabling automatic setup. Use a verified, fixed release and explicitly approve local changes. Check its cross-agent skill synchronization settings and limit Skio permissions to the reads you need. The remote installer contents remain unverified; no malicious behavior was established.

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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied command performs remote script execution rather than searching or reading Skio data. Although installation can be a supporting implementation detail, this chunk establishes no relationship between the Oomol installer and the declared Skio functionality. The downloaded script is not supplied, so its specific actions cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes a remotely fetched, unpinned script directly into Bash, allowing the delivered content to execute with the agent's local permissions without prior verification. The PowerShell alternative has the same weakness; compromise of the distribution endpoint could turn legitimate dependency setup into arbitrary code execution, although the file provides no evidence of an actual compromise.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

The fallback setup installs and executes remote software without warning about local system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The fallback instructs the agent to install software when the CLI is missing, without first explaining local changes or obtaining explicit installation approval. A request to read Skio data does not inherently authorize executing an installer with the agent's local permissions; the missing-command condition limits exposure but does not establish that authorization.

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 79)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