Back to skill

Security audit

ClickSend

Security checks for vulnerabilities and agentic risk

Overview

The ClickSend workflow includes sensible approval rules, but its setup can execute downloaded code and introduce broader agent changes without clear user approval.

Review and approve the CLI installation separately before allowing setup commands. Consider disabling automatic skill synchronization using the publisher-documented OO_SKILLS_SYNC_DISABLED setting ([command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md)). OOMOL mediates access to your connected ClickSend account. Retain the skill's approval requirements for sending messages and changing or deleting contacts. No malicious behavior was established, but the remote installer could not be inspected.

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 (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied code executes an Oomol-hosted installer rather than performing the declared ClickSend operations. Nothing in the chunk establishes this installation as a supporting dependency for ClickSend. The downloaded script's contents are not supplied, so its additional effects cannot be determined.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
86% confidence
Finding

The supplied code only invokes a CLI login command and contains no ClickSend-specific operations or configuration. Authentication could be a supporting implementation detail if linked to ClickSend, but no such connection is established in this chunk. Its visible primary behavior therefore differs from the declared purpose.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an unpinned remote installer directly into bash executes its contents without prior inspection or independent integrity verification. HTTPS protects transport but does not prevent malicious changes following compromise of the distribution service; the fallback-only context reduces exposure frequency, not the potential impact.

Content

Scanner excerpt · SKILL.md (reported line 67)May include surrounding context.

Fallback setup executes remote installation scripts without warning about local code execution or system changes.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The fallback directs the agent to execute downloaded shell or PowerShell code without explaining local system changes or obtaining installation-specific approval. Although installation is conditional on a missing dependency, a ClickSend request can thereby become local code execution; a compromised installer could access files and credentials available to the executing user.

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 88)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