The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill operates by reading, analyzing, and editing user-supplied LaTeX files and notes, which introduces a potential attack surface for indirect prompt injection if those files contain malicious instructions.
Ingestion points: The agent processes user-provided .tex files and free-text notes as part of the core dialogue workflow described in SKILL.md and README.md.
Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for the agent when processing external content.
Capability inventory: The skill is configured with access to Read, Write, Edit, and Bash tools in the SKILL.md frontmatter.
Sanitization: There is no evidence of sanitization, escaping, or validation being applied to the ingested LaTeX content or notes.

interactive-intro-writer