Back to skill

Security audit

Instabot

Security checks for vulnerabilities and agentic risk

Overview

The Instabot workflow includes approval safeguards, but automatic software installation and broader CLI side effects need review.

Review and approve CLI installation separately, preferably using a verified, pinned release. Check its automatic skill synchronization; upstream documents OO_SKILLS_SYNC_DISABLED=1 to disable it. Connect Instabot only if you trust OOMOL with that access, and retain approval for data changes. The remote installer contents 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
  • 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
97% confidence
Finding

The supplied command performs remote script execution for an Oomol installer rather than any visible Instabot operation. Although installation can be a supporting implementation detail, the supplied content establishes no relationship between this installer and the declared Instabot functionality. The downloaded script's further behavior cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes a mutable remote script directly into Bash without pinning a version or verifying its integrity before execution. A compromised distribution endpoint could execute arbitrary code with the agent's local privileges; HTTPS and the legitimate CLI dependency reduce suspicion of malicious intent but do not remove this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

Fallback setup executes remote installation scripts without warning the user about system changes or obtaining approval.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The fallback directs the agent to install software after a missing-command error without explicitly obtaining approval for local system changes. Although this is a legitimate dependency setup, the installation executes remotely supplied code with the invoking user's privileges, extending an Instabot data request into local code execution.

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 82)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