ClawHub

Aport Standup

Security checks across malware telemetry and agentic risk

Overview

This instruction-only skill is purpose-aligned for generating standups from APort decision records, but users should be aware it fetches external work-history data.

Install only if you want your agent to use APort decision history for standups. Confirm `APORT_AGENT_ID` points to the intended agent, avoid using it in chats where work-history or blocker details should not be revealed, and review the separate APort setup tools before running `npx aport-id` or following external setup instructions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The invocation guidance is broad enough to trigger on common requests like 'what did I do yesterday?' or 'what have you been doing?', which can cause the agent to fetch and summarize external APort decision history without an explicit, informed user request to access that system. Because the skill is framed as a normal standup helper, the user may not realize it will query signed activity records and reveal audit-style metadata rather than relying only on local conversation context.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs the agent to use an environment variable (APORT_AGENT_ID) and fetch decision history from a remote API, but it does not require a user-facing notice or consent flow before accessing potentially sensitive work-history and audit data. This creates a privacy and data-governance risk: an agent could silently use configured credentials/identifiers to retrieve and expose operational history, including blocked tasks and timestamps, in response to an ordinary productivity request.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal