skills/firecrawl/openclaw/wacli/Gen Agent Trust Hub

wacli

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the wacli CLI tool from a third-party GitHub repository (github.com/steipete/wacli) using Homebrew or Go during the installation phase.
  • [COMMAND_EXECUTION]: The skill uses the wacli command to perform various operations, including authentication (wacli auth), message retrieval (wacli messages search), and file transmission (wacli send file).
  • [INDIRECT_PROMPT_INJECTION]: The skill reads untrusted data by syncing and searching WhatsApp message history.
  • Ingestion points: WhatsApp chat messages and history synced via wacli messages search and wacli sync (SKILL.md).
  • Boundary markers: None specified; the instructions do not guide the agent to use delimiters or ignore instructions found within the retrieved messages.
  • Capability inventory: The skill can send text and files to external numbers, execute shell commands via the CLI, and access the local file system to send attachments.
  • Sanitization: No explicit sanitization or validation of the retrieved message content is performed before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:54 PM
Security Audit — agent-trust-hub — wacli