The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external URLs and GitHub repositories to create content, which is a potential surface for indirect prompt injection.
Ingestion points: Processes content via WebFetch, GitHub API calls, and the var selector input.
Boundary markers: The skill does not define specific delimiters or instructions to the agent to ignore embedded commands in the source data.
Capability inventory: The skill possesses the ability to write to the local filesystem and execute a local notification script.
Sanitization: No explicit sanitization or filtering logic is provided for the external data fetched during the research phase.
[COMMAND_EXECUTION]: The skill uses shell commands and script execution for its workflow.
Evidence: Uses mkdir -p for directory management and executes a local ./notify utility to alert the user of script completion.

video-script