The Agent Skills Directory

Indirect Prompt Injection (LOW): The skill's primary purpose is to ingest and analyze external data (other skill files), which creates a potential vulnerability surface.
Ingestion points: The skill utilizes Read, Glob, and Grep tools to pull content from other files in the environment into the agent's context.
Boundary markers: Absent. There are no instructions or delimiters defined to help the agent distinguish between its core logic and potentially malicious instructions embedded in the skills being reviewed.
Capability inventory: The skill is authorized to use high-impact tools including Bash, Write, Edit, and WebFetch. This broad toolset increases the risk if an indirect prompt injection were to successfully manipulate the agent's behavior.
Sanitization: Absent. There is no mechanism described for sanitizing or validating the content of the skills under review.

skill-reviewer