The Agent Skills Directory

[SAFE]: The skill provides instructions and examples for using the spark CLI to manage shared inboxes and team assignments. All operations are consistent with the skill's stated purpose.
[COMMAND_EXECUTION]: The skill instructs the agent to execute spark commands for listing teams, reading emails, and performing actions like assignments or comments. These are documented tools for the Spark platform and do not involve arbitrary shell execution or system modification.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted data from email bodies via the spark thread command.
Ingestion points: Email content is read using spark thread <id> in SKILL.md.
Boundary markers: None identified.
Capability inventory: The skill can perform assignments (spark action assign), modify status (spark action markAsDone), and add comments (spark comment) based on the content read.
Sanitization: No specific sanitization or filtering of email content is described.
Assessment: This is a low-risk surface inherent to the skill's primary function of email triage.

spark-persona-team-lead