The Agent Skills Directory

[NO_CODE]: The skill consists entirely of markdown instructions (SKILL.md) and does not include any executable scripts, configuration files, or external dependencies.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and store information ('lessons') derived from the session context. While this involves processing untrusted data, the instructions include specific security safeguards to 'Reject credentials, private data, confidential prompts, and sensitive raw output.' These constraints, combined with the requirement for human selection when updating team records, effectively mitigate the risk of processing malicious injected content.

remember