Back to skill

Security audit

KrispCall

Security checks for vulnerabilities and agentic risk

Overview

The KrispCall integration is coherent, but its setup fallback executes downloaded code without verification or explicit installation approval.

Review setup before installing. Install and verify the required CLI separately, and approve any additional agent skills it installs or updates. OOMOL will mediate access to your connected KrispCall account. Retain the skill's confirmation requirements for changes and deletions. The remote installers were unavailable for inspection, so their full local effects remain uncertain.

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
96% confidence
Finding

The supplied command installs software from Oomol rather than interacting with KrispCall. Nothing in the supplied chunk establishes this installation as a supporting dependency for the declared purpose. The remote script's contents are unavailable, so its further effects cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes a remotely retrieved, mutable script directly into Bash without integrity verification or an opportunity to inspect it; the PowerShell alternative has the same issue. A compromised distribution endpoint could execute arbitrary code with the invoking user's privileges, exposing local files and credentials even though KrispCall tokens are injected server-side.

Content

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

The setup fallback executes remote installation scripts without warning the user about local system changes.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The fallback instructs the agent to install software after a missing-command error without first obtaining approval for local system changes. Although conditional and relevant to the integration, this expands a KrispCall data request into local code execution and installation; the declared tool restriction may limit execution but does not make the instruction safe.

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