The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted natural language data such as essays, debate transcripts, or conversational excerpts. This represents an inherent attack surface for indirect prompt injection.\n
Ingestion points: SKILL.md workflow section accepts free-form text and conversational transcripts as input for analysis.\n
Boundary markers: The skill instructions do not specify the use of delimiters or 'ignore' instructions for the processed data.\n
Capability inventory: The skill is configured with access to Read, Write, Edit, Glob, and Grep tools for generating deliverables.\n
Sanitization: No specific sanitization or validation of input text is defined in the instructions.

toulmin-argument-analysis