Back to skill

Security audit

airfocus

Security checks for vulnerabilities and agentic risk

Overview

The airfocus workflow is coherent, but its automatic setup can execute unverified remote code without a separate installation approval.

Review and approve CLI installation separately, including any changes to installed agent skills; prefer a pinned, verified release. OOMOL mediates access to your connected airfocus account, so limit its permissions and confirm exact writes and deletions. The remote installer and hosted connector implementation were unavailable for review.

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 installer hosted on an unrelated domain rather than performing any visible airfocus operation. Nothing in the supplied chunk establishes this installation as a supporting implementation detail for airfocus. The downloaded script's contents and further effects are not available for assessment.

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 43)May include surrounding context.

md
- `create_item` — Create an item in an airfocus workspace. [write]
- `delete_item` — Permanently delete an item from an airfocus workspace. [destructive]
- `get_item` — Get one item from an airfocus workspace by ID.
- `get_profile` — Get the profile associated with the connected airfocus personal access token.
- `get_workspace` — Get one airfocus workspace by ID.
- `search_items` — Search items in an airfocus workspace with optional filter and sort criteria.
- `search_workspaces` — Search airfocus workspaces with optional archived, filter, and sort criteria.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a mutable remote installer directly into bash executes its contents without version pinning or independent integrity verification; the PowerShell alternative has the same issue. HTTPS protects transport but does not protect against a compromised distribution endpoint or malicious installer update, which could execute arbitrary code with the user's permissions.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

The setup workflow executes downloaded installation scripts without warning the user about system changes.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The fallback directs the agent to install software by executing a remote script without first explaining local system changes or obtaining installation-specific approval. Although triggered only when the CLI is missing, this expands an airfocus data task into local code execution with the invoking user's permissions; the airfocus write-confirmation rules do not cover this setup operation.

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 83)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