The Agent Skills Directory

[PROMPT_INJECTION]: The skill provides an interface to ingest content from Confluence, which is an external, collaborative source where malicious actors could embed instructions to influence the agent.
Ingestion points: The skill utilizes confluence.get_page_by_id, confluence.get_page_by_title, and confluence.get_all_pages_from_space to retrieve documentation content (SKILL.md).
Boundary markers: No specific boundary markers or instructions are provided to help the agent distinguish between data retrieved from Confluence and its own core instructions.
Capability inventory: The agent has access to Bash, Read, Write, and Edit tools, which could be misused if the agent inadvertently follows instructions embedded in a wiki page (SKILL.md frontmatter).
Sanitization: The provided implementation examples do not show content sanitization or validation of the retrieved wiki storage format data.

confluence