The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from WPS notes, which serves as a potential vector for indirect prompt injection if the notes contain malicious instructions.
Ingestion points: Content enters the agent's context through tools like read_note and get_note_outline as described in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the document content.
Capability inventory: The skill possesses write capabilities through the batch_edit operation (SKILL.md), allowing it to modify the note based on its analysis.
Sanitization: There is no documentation of sanitization or validation logic to filter out potential instructions from the document text before processing.

wpsnote-beautifier