The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes the contents of terminology.md, which could be used as a vector for indirect prompt injection if the file contains instructions disguised as terminology.
Ingestion points: Reads the root terminology.md file and specific topic files mentioned in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or "ignore instructions" warnings when processing the file content.
Capability inventory: The skill is limited to providing explanations and code documentation; no file-writing, network operations, or command execution capabilities are present.
Sanitization: There is no evidence of sanitization or filtering of the terminology file content before it is incorporated into the agent's context.

use-terminology