The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill acts on untrusted data provided by the user in the form of demand analysis reports or verbal descriptions, creating a potential vector for indirect instructions.
Ingestion points: The workflow in SKILL.md (Step 1) explicitly instructs the agent to read and extract information from external report files.
Boundary markers: The instructions do not specify any delimiters (like XML tags or markdown blocks) or safety warnings to ignore embedded instructions within the source documents.
Capability inventory: The skill utilizes file system capabilities to read source documents and write the final technical design as a new Markdown file (SKILL.md Step 4).
Sanitization: There is no evidence of input validation, escaping, or content filtering to prevent the agent from executing instructions hidden in the requirement reports.

tech-design