The Agent Skills Directory

PROMPT_INJECTION (LOW): The skill possesses a surface for indirect prompt injection. It instructs the agent to fetch documentation via mcp__context7__query-docs and describes an OpenApiAggregationService that pulls JSON data from remote URLs.
Ingestion points: mcp__context7__query-docs in SKILL.md and OpenApiAggregationService.GetAggregatedOpenApiAsync() in references/workflows.md fetch content from external sources.
Boundary markers: Absent. No delimiters are provided to distinguish instructions from fetched data.
Capability inventory: The skill allows high-privilege tools including Bash, Write, and Edit as declared in the SKILL.md frontmatter.
Sanitization: Absent. No validation or filtering is performed on the ingested documentation or API schemas before processing.
COMMAND_EXECUTION (LOW): The skill utilizes the Bash tool for standard development tasks such as running services via dotnet run and testing endpoints with curl. These operations are conducted with appropriate context and do not attempt to escalate privileges or access sensitive system files.

scalar