The Agent Skills Directory

[Indirect Prompt Injection] (LOW): The skill is designed to ingest and act upon external findings, creating a surface where malicious instructions in analyzed data could potentially be executed. 1. Ingestion points: Ingests process maps and findings from external tools like system-reviewer. 2. Boundary markers: The skill documentation lacks delimiters or specific instructions to ignore embedded commands within the analyzed data. 3. Capability inventory: The skill has access to high-privilege tools including Bash, Write, Edit, and WebFetch. 4. Sanitization: There is no evidence of input validation or sanitization mechanisms for external data before it influences tool use.- [No Code] (SAFE): The skill consists entirely of instructional markdown and metadata with no executable scripts or binary files, reducing the risk of direct malicious behavior.

process-optimizer