The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes a local Python script via python3 ${CLAUDE_PLUGIN_ROOT}/tools/scrivener/cli.py to inspect and modify Scrivener binder documents. This execution is confined to managing document text and formatting as part of the skill's stated purpose.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by reading and processing the contents of user-controlled Scrivener RTF files.
Ingestion points: Untrusted data is ingested via the read <id> command into the agent's context as specified in SKILL.md.
Boundary markers: There are no documented delimiters or instructions designed to isolate user-provided text from the agent's control instructions.
Capability inventory: The skill possesses capabilities for reading document content (read), writing text (set-text), and executing project-wide formatting changes as described in SKILL.md and references/formatting-model.md.
Sanitization: No sanitization or filtering of the document text is mentioned in the provided instructions or reference materials.

scrivener-formatting