The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown instructions and does not include any executable scripts, binary files, or external code dependencies.
[SAFE]: The instructions include a specific security protocol requiring the agent to verify that any user-provided webhook_url uses HTTPS and is under the user's control before proceeding with configuration.
[PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from external websites, creating a surface for indirect prompt injection.
Ingestion points: External web content (news, competitor sites, product updates) monitored via the 'scout' tools.
Boundary markers: Absent; the instructions do not define specific delimiters or instructions to treat fetched content as untrusted data.
Capability inventory: The skill uses create_scout, edit_scout, and get_scout_updates to manage persistent monitoring and retrieve data.
Sanitization: No sanitization, escaping, or filtering of the external content is described in the setup process.

yutori-scout