The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the alera CLI tool to manage agent automations, including creating, editing, and running scheduled tasks. This is the intended primary purpose of the skill and aligns with the toolset provided by the author.
[INDIRECT_PROMPT_INJECTION]: The skill enables users to define and run automated agent prompts, which establishes an attack surface for indirect prompt injection if those automations process data from untrusted sources.
Ingestion points: Prompt content is ingested via CLI flags like --prompt and --prompt-file in SKILL.md, and the promptTemplate JSON field described in references/authoring.md.
Boundary markers: The documentation does not specify the use of delimiters or explicit instructions to the agent to ignore instructions embedded in the data being processed.
Capability inventory: The alera automation run-now command allows for the immediate execution of defined automations, which can operate within workspaces and potentially interact with project files as described in the worktree and project-checkout targets.
Sanitization: There are no sanitization or validation steps mentioned for the content provided to the automation prompts.

alera-automations