The Agent Skills Directory

[SAFE]: The skill does not contain any malicious code, obfuscation, or unauthorized data access patterns. All operations, such as file creation and integration access, are transparently described as part of the co-authoring workflow.
[PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection by reading external context from files, links, and workspace integrations (Slack, Google Drive). However, this data ingestion is the primary function of the skill, and the workflow incorporates a 'Reader Testing' stage to mitigate potential misinterpretations by testing content clarity with independent agent instances.

doc-coauthoring