Back to skill

Security audit

Attio

Security checks for vulnerabilities and agentic risk

Overview

The Attio operations have clear approval controls, but setup can execute downloaded installation code without separate approval or integrity verification.

Review the installation fallback before enabling this skill. Prefer a trusted CLI installed beforehand, or separately inspect and approve a version-pinned, integrity-verified installation. OOMOL mediates your Attio access, so grant only necessary permissions and retain the documented change and deletion confirmations. The remote installer and connector 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied code executes an Oomol-hosted installation script rather than performing Attio operations. No Attio integration or dependency relationship is shown that would establish this as a supporting implementation detail. The remote script's contents and downstream effects cannot be determined from the supplied chunk.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.

md
- `delete_record` — Delete a single Attio record by object and record ID. [destructive]
- `get_object` — Get one Attio object by object ID or API slug.
- `get_record` — Get a single Attio record by object and record ID.
- `identify` — Identify the current Attio access token, its workspace, and the scopes attached to it.
- `list_attributes` — List attributes defined on an Attio object or list.
- `list_objects` — List all system-defined and user-defined objects in an Attio workspace.
- `list_records` — List Attio records for an object with optional filtering, view filtering, sorting, limit, and offset.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

Piping an HTTPS response directly into bash executes mutable remote code without a pinned version or independent integrity verification. Compromise of the installer distribution could therefore yield arbitrary code execution with the invoking user's permissions; the PowerShell alternative has the same underlying risk.

Content

Scanner excerpt · SKILL.md (reported line 64)May include surrounding context.

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

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The fallback directs the agent to execute remote installation scripts without explicitly obtaining approval for local software installation or explaining that downloaded code will run with the user's privileges. Requiring a missing-CLI error limits when this occurs, but does not authorize the resulting local changes or mitigate execution of a compromised installer.

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 85)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