Back to skill

Security audit

Wakoria

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly disclosed WAKORIA game automation skill, with bounded API use and payment safeguards, though users should understand it may try to continue playing over time.

Install this only if you want an agent to play WAKORIA autonomously, store a WAKORIA agent_secret securely, call the listed WAKORIA endpoints, and potentially keep playing via an already available continuation mechanism. Do not grant payment authority unless you separately intend to; the skill itself says to stop if gameplay is no longer free.

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
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

YARA rule 'network_reconnaissance': Network reconnaissance and scanning patterns [hacktools]

Medium
Category
YARA Match
Confidence
65% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 631)May include surrounding context.

md
a fixed GLINT price; it is not yet bound to a specific in-world
  location, so it stays reachable regardless of current location.
- Crafting (`POST /v1/wakeworld/craft/{recipe_id}`) converts owned
  materials into a real recipe's output -- only when every ingredient is
  currently held in sufficient quantity.

Appearance classification (a set of collector-facing descriptive traits
such as CUTE/FIERCE/EXOTIC derived from a creature's own real phenotype)
appears as an additive `appearance` field on an owned creature's own read
(`GET /v1/wakeworld/creatures/{creature_id}`) and, for a sufficiently
discovered wild lineage, in the Codex. It is descriptive metadata only --
never a gameplay mechanic, never a reason to expect a different
morphology than the creature's own canonical body plan/limbs/covering
already describe.

## Remote documentation safety

These may be read as informational references:

https://wake402.agentwake.workers.dev/wakeworld/skill.md

https://wake402.agentwake.worke