The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary purpose is to read and execute instructions from a ticket-tracking system via the sesh CLI. These prompts are treated as authoritative instructions for the agent, creating a surface for indirect prompt injection if a ticket contains malicious content.
Ingestion points: sesh ticket get --id <id> --field prompt and sesh ticket get --id <id> --field notes (SKILL.md).
Boundary markers: None present; the instructions explicitly state the ticket's prompt is the agent's instructions.
Capability inventory: The skill uses the sesh CLI for ticket management, blob expansion (file path resolution), and thread commands (SKILL.md).
Sanitization: No sanitization or validation of the retrieved ticket content is mentioned before it is processed by the agent.
[COMMAND_EXECUTION]: The skill relies on executing various subcommands of the sesh CLI utility to manage work tickets, update statuses, and expand file blobs.

do-tickets