ClawHub
Back to skill

Security audit

github-initiative-pulse

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only GitHub reporting helper; its main issue is overly broad trigger words that may activate it more often than intended.

Before installing, consider narrowing the trigger phrases so the skill activates only for GitHub initiative or milestone reporting requests. The inspected artifacts do not show hidden execution, credential handling, persistence, or automatic posting.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
97% confidence
Finding

The trigger "status" directly conflicts with a common built-in command name and is highly likely to shadow or hijack routine agent operations. This can cause the skill to activate when a user intends to invoke a platform status command, leading to unexpected behavior and making command routing less predictable and less safe.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes broad generic terms like "github," "projects," "reporting," and "status," which are likely to match many ordinary user requests unrelated to this skill. Over-broad activation increases the chance of unintended invocation, causing prompt-context pollution, accidental execution of the wrong workflow, or interference with more appropriate skills.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.