Security audit

Openclaw Skill Parallel Tasks

Security checks for vulnerabilities and agentic risk

Overview

This skill openly runs multiple agent tasks in parallel, but its broad activation and unbounded task dispatch deserve user review before installation.

Install only if you deliberately want a skill that can fan out multiple agent sessions. Use it with explicit task lists, low concurrency, and trusted inputs; avoid giving it broad file-write, account-changing, or public-posting tasks unless you are prepared to review the effects of each spawned session.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (16)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 52)May include surrounding context.
md
### CLI Usage (scripts/executor.ts)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.
md
### CLI Usage (scripts/executor.ts)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.
md
### CLI Usage (scripts/executor.ts)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 64)May include surrounding context.
md
### CLI Usage (scripts/executor.ts)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 297)May include surrounding context.
md
### CLI Usage (scripts/executor.ts)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 311)May include surrounding context.
md
### CLI Usage (scripts/executor.ts)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 317)May include surrounding context.
md
### CLI Usage (scripts/executor.ts)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 326)May include surrounding context.
md
### CLI Usage (scripts/executor.ts)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 337)May include surrounding context.
md
### CLI Usage (scripts/executor.ts)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 346)May include surrounding context.
md
### CLI Usage (scripts/executor.ts)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The README explicitly promotes batch file operations including read/write in parallel but does not warn about the risk of concurrent data modification, overwrites, race conditions, or accidental destructive changes. In the context of a parallel-execution skill, missing safety guidance is more dangerous because simultaneous writes can amplify mistakes and make recovery harder.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The trigger description uses broad natural-language phrases such as 'run these in parallel' and 'concurrent tasks', which can match ordinary user intent too loosely and cause the skill to activate unexpectedly. In an agent environment, over-broad activation can route benign requests into a high-capability skill that spawns multiple operations at once, increasing the chance of unintended actions, resource overuse, or unsafe parallel execution.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 77% confidence
Finding: The skill documents process-spawning behavior and interaction with the Hermes CLI, but it declares no explicit tool scope or permissions boundaries. In an agent environment, missing scope metadata can allow the skill to be invoked with broader-than-expected capabilities, increasing the chance of unintended command execution or environment access.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The description uses broad natural-language triggers such as 'run these in parallel' and 'concurrent tasks,' which are common phrases that may appear in ordinary user requests. This can cause accidental activation of a skill that spawns multiple subprocess-like sessions, magnifying the effect of a mistaken invocation and potentially launching tasks the user did not explicitly authorize.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The 'When to Use' section defines activation conditions with ambiguous phrases like 'user wants faster results' and 'multiple independent tasks need to be executed at once,' which are subjective and easy to over-match. Because this skill can initiate concurrent task execution, ambiguous routing increases the risk of unnecessary parallel runs, resource exhaustion, or execution of unintended actions.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The executor forwards task.description directly to an external agent CLI (hermes cli with sessions_spawn), causing arbitrary user-supplied content to be transmitted for downstream execution without any confirmation, warning, or trust boundary enforcement. In the context of a parallel-execution skill, this increases the chance that sensitive instructions, secrets, or destructive task requests are fanned out to multiple subprocesses at once, amplifying impact if the input is unsafe or attacker-controlled.
Content: No source excerpt is available for this finding.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: scripts/executor.ts:192