ClawHub
Back to skill

Security audit

Ashen Era Playtest

Security checks for vulnerabilities and agentic risk

Overview

The skill is a narrow local launcher for a CLI game report workflow, with no evidence of hidden network access, credential handling, persistence, or destructive behavior.

Install only if you are comfortable letting the agent run a local CLI game launcher. Use the documented play command and avoid passing arbitrary subcommands or debug-style options; also note that this inspected package did not include the release archives it claims to bundle, so it may not function as published.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
The documented behavior promises a tightly constrained `play` flow, but the finding indicates the implementation actually defaults to `--help`, passes through arbitrary CLI arguments, and does not enforce the stated bans on `autoplay`, cheats, debug modes, or locale. This mismatch is dangerous because users and higher-level agents may trust the skill description while the runtime behavior permits unintended or potentially unsafe execution paths.

Lp3

Medium
Category
MCP Least Privilege
Confidence
96% confidence
Finding
The skill explicitly instructs use of shell-based execution (`bash`, launcher scripts, archive handling) but does not declare any tool scope or allowed-tools restrictions. That means an agent may invoke shell capabilities without a policy boundary, increasing the chance of unintended command execution or expansion of capability beyond what the skill actually needs.

Natural-Language Policy Violations

Low
Confidence
96% confidence
Finding
The default prompt explicitly requires the run to be performed and reported 'in English.' This is a natural-language policy concern because it imposes a language choice without indicating user selection, opt-in, or a documented locale-specific justification.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The file states that the default locale is `en` and only mentions switching to `zh` if the user explicitly wants Chinese. This creates a language-policy constraint that favors English by default rather than offering a neutral language choice or broader opt-in.

Static analysis

No suspicious patterns detected.