Back to skill

Security audit

OpenBuddy 电子宠物

Security checks for vulnerabilities and agentic risk

Overview

OpenBuddy is a terminal virtual pet skill that stores a small local pet-state file and does not show network, command-execution, credential theft, or destructive behavior.

Install only if you are comfortable with a Chinese-language terminal pet that creates a local ~/.openbuddy/buddy-soul.json file. Use OPENBUDDY_DIR to choose a different storage location, and avoid putting sensitive personal identifiers in OPENBUDDY_USER_ID.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (15)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill documents use of environment-derived identity and storage behavior but does not declare an explicit tool scope or permissions model. In an agent ecosystem, missing scope boundaries can cause the skill to access environment-provided data implicitly, reducing transparency and increasing the chance of unintended data exposure or execution beyond user expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The entire skill description, usage guidance, and interaction model are presented only in Chinese, with no indication that users can opt into another language. Under the language/locale policy, a skill should not impose a specific language unless the constraint is clearly documented and justified or users are offered a choice.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill states that part of the pet state is persisted to ~/.openbuddy/buddy-soul.json but does not prominently warn users in the main behavior description that local data will be stored. Persistent storage without clear notice can surprise users, create privacy concerns, and leave residual data on shared or managed systems.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger terms are broad everyday words such as “buddy”, “宠物”, and “伙伴”, which can match ordinary conversation and activate the skill unexpectedly. Unintended activation can lead to unsolicited command suggestions or execution paths involving local scripts and persistent state, violating user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This JavaScript file presents its user-facing description, usage text, command help, and runtime output in Chinese only. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified, which is not present here.

Content

No source excerpt is available for this finding.

Context Window Stuffing

Medium
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

Content

Scanner excerpt · buddy.js (reported line 369)May include surrounding context.

js
const buddy = mergeBonesSoul(bones, soul);

  console.log('\u2554\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2557');
  console.log('\u2551        \ud83d\udc3e OpenBuddy \u5361\u7247 \ud83d\udc3e       \u2551');
  console.log('\u2560\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2563');
  console.log('\u2551                                  \u2551');

Context Window Stuffing

Medium
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

Content

Scanner excerpt · buddy.js (reported line 404)May include surrounding context.

js
const buddy = mergeBonesSoul(bones, soul);

  console.log('\u2554\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2557');
  console.log('\u2551        \ud83d\udc3e OpenBuddy \u5361\u7247 \ud83d\udc3e       \u2551');
  console.log('\u2560\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2563');
  console.log('\u2551                                  \u2551');

Context Window Stuffing

Medium
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

Content

Scanner excerpt · buddy.js (reported line 371)May include surrounding context.

js
console.log('\u2554\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2557');
  console.log('\u2551        \ud83d\udc3e OpenBuddy \u5361\u7247 \ud83d\udc3e       \u2551');
  console.log('\u2560\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2563');
  console.log('\u2551                                  \u2551');

  const { lines } = renderSprite(buddy.species, buddy.hat, 0);

Context Window Stuffing

Medium
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

Content

Scanner excerpt · buddy.js (reported line 380)May include surrounding context.

js
console.log('\u2554\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2557');
  console.log('\u2551        \ud83d\udc3e OpenBuddy \u5361\u7247 \ud83d\udc3e       \u2551');
  console.log('\u2560\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2563');
  console.log('\u2551                                  \u2551');

  const { lines } = renderSprite(buddy.species, buddy.hat, 0);

Context Window Stuffing

Medium
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

Content

Scanner excerpt · buddy.js (reported line 388)May include surrounding context.

js
console.log('\u2554\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2557');
  console.log('\u2551        \ud83d\udc3e OpenBuddy \u5361\u7247 \ud83d\udc3e       \u2551');
  console.log('\u2560\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2563');
  console.log('\u2551                                  \u2551');

  const { lines } = renderSprite(buddy.species, buddy.hat, 0);

Context Window Stuffing

Medium
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

Content

Scanner excerpt · buddy.js (reported line 400)May include surrounding context.

js
console.log('\u2554\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2557');
  console.log('\u2551        \ud83d\udc3e OpenBuddy \u5361\u7247 \ud83d\udc3e       \u2551');
  console.log('\u2560\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2563');
  console.log('\u2551                                  \u2551');

  const { lines } = renderSprite(buddy.species, buddy.hat, 0);

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The documented OPENBUDDY_USER_ID environment variable influences deterministic pet generation, but the skill does not warn that user identifiers may be sensitive or linkable across sessions. Using identifiers from the environment without privacy guidance can expose users to tracking, correlation, or accidental disclosure in logs and screenshots.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The manifest describes an electronic pet system for hatching and interacting with a terminal companion. This code reads hostname and username environment variables to build a user identifier, which is then used to deterministically assign pet traits; while local persistence is expected, collecting host identity information is not an obvious requirement for a virtual pet and exceeds the minimally justified capability for the stated purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The file contains natural-language comments in Chinese only (for example, the header comments describing the sprite sheet). This imposes a specific language for maintainers or users reading the file, with no opt-in or documented justification, which matches the locale/language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The comment labeling the hats sprite sheet is written only in Chinese. As with the earlier comments, this is a natural-language language-choice constraint without any visible opt-in or justification in the file.

Content

No source excerpt is available for this finding.