The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the wacli binary from a third-party Homebrew tap (steipete/tap/wacli) and a GitHub repository (github.com/steipete/wacli). These sources are not affiliated with the skill author or a trusted vendor.- [COMMAND_EXECUTION]: The skill executes multiple shell commands through the wacli CLI, including wacli auth, wacli sync, wacli messages search, and wacli send, which could allow for unintended command behavior if parameters are manipulated.- [DATA_EXFILTRATION]: The skill accesses and processes sensitive user data by searching and syncing WhatsApp chat history. It also includes capabilities to send local files (e.g., wacli send file --file /path/agenda.pdf) to remote WhatsApp JIDs, creating a path for data exfiltration.- [PROMPT_INJECTION]: The skill processes untrusted external data via the wacli messages search command, which retrieves content from WhatsApp messages. This creates an attack surface for indirect prompt injection.
Ingestion points: Results from wacli messages search and wacli chats list are processed by the agent.
Boundary markers: The skill does not define specific delimiters or instructions to the agent to ignore commands within the fetched message content.
Capability inventory: The skill has the ability to execute shell commands (wacli), read local files, and send messages/files to external recipients.
Sanitization: There is no evidence of sanitization or filtering of the content retrieved from WhatsApp before it is presented to the agent.

wacli