The Agent Skills Directory

[PROMPT_INJECTION]: The skill is designed to ingest and analyze external text (events, communications, media coverage) which creates a surface for indirect prompt injection attacks. \n- Ingestion points: Event descriptions and organizational narratives in SKILL.md. \n- Boundary markers: The instructions lack delimiters or explicit warnings to ignore instructions embedded within the analyzed data. \n- Capability inventory: No executable scripts or tool-calling restrictions are included in the skill. \n- Sanitization: No validation or escaping of input content is defined. \n- [NO_CODE]: The skill consists entirely of markdown documentation and metadata with no executable scripts, binaries, or shell commands.

novelist-analyst