The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface arising from its core functionality.
Ingestion points: External content is ingested via handover.read_artifact, handover.thread, and handover.annotations in SKILL.md.
Boundary markers: No delimiters or 'ignore' instructions are provided to isolate untrusted content from the agent's instructions.
Capability inventory: The skill can perform write actions including handover.comment, handover.annotate, handover.assign, and handover.update_comment as seen in SKILL.md.
Sanitization: There is no evidence of sanitization or validation of the retrieved content.
[SAFE]: The skill follows operational best practices by requiring identity verification through handover.whoami and emphasizing revision-anchored annotations.

handover-review