Back to skill

Security audit

Async Command

Security checks for vulnerabilities and agentic risk

Overview

This is a small instructional skill about running long commands asynchronously, with no bundled code, persistence, credential handling, or hidden behavior.

This skill is reasonable to install if you want guidance on long-running command workflows. Before using its stop guidance, consider whether the active command is safe to interrupt, especially for migrations, installs, deployments, or data-processing jobs.

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
  • 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 (3)

Unbounded Resource Access

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.

Content

Scanner excerpt · SKILL.md (reported line 52)May include surrounding context.

Step 2: Manage the background job

python
# Check if done
process(action="poll", sessionId="<session_id>", timeout=0)

# Wait for completion
process(action="poll", sessionId="<session_id>", timeout=60000)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill explicitly instructs users to kill background jobs immediately on a generic stop signal, but it does not warn that terminating active builds, migrations, installs, or training jobs can leave partial state, corrupt outputs, or lose unsaved work. In this context, the omission is risky because the same document encourages async use for operations that may be stateful or destructive.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The file includes Chinese-language stop wording and a Chinese-only mental-model section, which imposes a locale-specific experience in the instructions. The policy requires avoiding language constraints unless the skill offers language choice or clearly justifies the locale limitation.

Content

No source excerpt is available for this finding.