Back to skill

Security audit

Habitica

Security checks for vulnerabilities and agentic risk

Overview

This Habitica helper needs review because setup runs an unchecked downloaded installer and its safety rules incorrectly treat task scoring as read-only.

Before using this skill, have its scoring action classified as a write requiring approval of the task, direction, and effect. Install the CLI through a separately reviewed process and check its additional skill-installation behavior. Habitica access is mediated by OOMOL, so consider that service's credential access and billing. The submitted text supports these review concerns, but does not establish malicious intent; external installers and connector implementation remain unverified.

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 command performs remote script execution rather than any visible Habitica operation. Nothing in the chunk establishes that this installer is a supporting dependency for Habitica functionality. The downloaded script's contents and any further effects are not available for assessment.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a remotely fetched installer directly into bash executes mutable third-party code with the agent process's local privileges, without a review or integrity-verification step. The conditional setup context makes installation relevant and reduces exposure frequency, but a compromised distribution endpoint or installer could still execute arbitrary code; the PowerShell example has the same weakness.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

The untagged score_task action changes Habitica state despite the safety claim that all untagged actions are reads.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The score_task action changes Habitica state, but it has no write tag and therefore falls under the explicit instruction that untagged actions are safe reads. This can bypass the skill's confirmation requirement and cause unintended task scoring and changes to character statistics or rewards.

Content

No source excerpt is available for this finding.

The untagged `score_task` action is incorrectly treated as a safe read, omitting a warning and confirmation for its state-changing effects.

Medium
Category
Output Handling
Confidence
99% confidence
Finding

The missing write classification incorrectly presents score_task as safe to execute without confirmation, even though scoring can alter task and character state. This is the same underlying issue as SDI-4, rather than an additional independent vulnerability.

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 86)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