The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from external sources (other agents) which could contain malicious instructions.
Ingestion points: Messages are retrieved into the agent's context using gc mail inbox, gc mail peek, gc mail read, and gc mail thread in SKILL.md.
Boundary markers: The instructions do not define delimiters or warnings to treat message content as untrusted data.
Capability inventory: The skill executes commands using the gc CLI utility as documented in SKILL.md.
Sanitization: No sanitization or validation of the message content is mentioned before it is processed by the agent.
[COMMAND_EXECUTION]: The skill relies on executing the gc command-line interface for messaging operations, including sending, reading, and deleting data.

gc-mail