The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use the listen command-line utility for sending notifications. This is a standard functional requirement for the skill's stated purpose and utilizes a vendor-provided tool.
[DATA_EXFILTRATION]: The skill facilitates sending data to an external notification service via a user-configured webhook. Security risks are mitigated by explicit instructions to the agent to exclude credentials, secrets, or large logs from notifications.
[PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection through its file-reading capabilities.
Ingestion points: The skill can read local files (e.g., ./report.md) via the --markdown-file argument.
Boundary markers: There are no explicit delimiters defined to isolate the content of these files from the agent's instructions.
Capability inventory: The skill utilizes the listen CLI to perform network-based notifications.
Sanitization: The skill relies on instructional constraints provided to the agent to avoid sensitive data and to summarize logs rather than programmatic sanitization.

listen-notifications