The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes content from external wiki files which may contain adversarial instructions.
Ingestion points: Reads local markdown files from the wiki/ directory using the Read tool.
Boundary markers: Absent; the instructions do not specify delimiters or warnings to ignore instructions embedded within the wiki pages.
Capability inventory: Uses Read, Glob, and Grep. The skill also instructs the agent to create new files in wiki/questions/ and append data to wiki/index.md and wiki/log.md, implying file-write capabilities.
Sanitization: Absent; there is no mention of validating or escaping content retrieved from the wiki before it is processed or synthesized into responses.

wiki-query