Back to skill

Security audit

Freshdesk

Security checks for vulnerabilities and agentic risk

Overview

The fallback setup directs the agent to execute downloaded installers without a separate approval step or integrity check.

Review and approve the CLI installation separately before allowing fallback setup. Prefer a reviewed, version-pinned installation. Connecting Freshdesk lets OOMOL handle access to account and ticket data; the bundled instructions do not establish the external CLI or installers' implementation.

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 code performs remote script execution rather than searching or reading Freshdesk data. Nothing in the supplied chunk establishes that the Oomol installer is a supporting dependency for Freshdesk access. The downloaded script's contents are not supplied, so its additional behavior cannot be determined.

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 mutable remote code with the agent's local privileges, without version pinning or independent integrity verification. Compromise of the distribution endpoint could expose accessible files and credentials or alter the host; the PowerShell example presents the same risk. The official-looking dependency context and missing-CLI condition do not establish the downloaded code's safety.

Content

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

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

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The missing-CLI fallback directs the agent to execute downloaded code without explaining that installation can modify the host or requiring user approval. Conditioning installation on a command failure reduces exposure, but a request to read Freshdesk data does not itself authorize local software installation; the Bash tool restriction may limit execution if strictly enforced.

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