Back to skill

Security audit

BidSketch

Security checks for vulnerabilities and agentic risk

Overview

The BidSketch reader fits its stated purpose, but its setup fallback executes unverified remote installers without a clear approval step.

Review and install the CLI yourself before enabling this skill, including any bundled-skill installation or synchronization. Prefer a pinned, verified release and require approval for setup changes. Connecting BidSketch allows OOMOL-mediated access to business records. The complete bundled artifact was inspected; scanner reference gaps were harmless text examples, while external installer behavior remains unverified. No artifact-backed malicious behavior was found.

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
99% confidence
Finding

The supplied code does not search or read BidSketch data. Instead, it executes an installer from a different service. No connection to the declared BidSketch functionality is shown, so this is not established as a supporting implementation detail. The downloaded script's subsequent behavior cannot be determined from the supplied chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an HTTPS response directly into bash executes remote code with the agent process's local permissions, without a pinned version or independent integrity verification. A compromised distribution endpoint or malicious installer update could expose accessible files and credentials or modify the host; the Windows irm-to-iex example has the same underlying risk.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

The setup workflow instructs the agent to execute a remotely downloaded installer without warning about local system changes or remote-code execution.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The fallback instructs the agent to install software by immediately executing downloaded code, without requiring user approval or explaining the resulting local system changes. Its missing-command prerequisite limits exposure, and the declared tool allowlist may block these commands, but neither makes the installation instructions safe if executed in a permissive environment.

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 81)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