The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external codebases, which inherently introduces a surface for indirect prompt injection where instructions embedded in analyzed files could attempt to influence the agent's behavior.
Ingestion points: Project source code is read using the Read, Grep, and Glob tools as defined in the allowed-tools section of SKILL.md.
Boundary markers: The instructions do not define specific delimiters or adversarial-intent warnings to distinguish analyzed code from agent instructions.
Capability inventory: The skill has permissions to modify files via Write and Edit, manage tasks with TaskCreate, and communicate via SendMessage and Teammate.
Sanitization: There is no explicit requirement for the agent to sanitize or filter the content of read files before processing them for quality metrics.

code-quality-analysis