The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to explore the local codebase to answer questions when applicable. This creates a potential vulnerability where malicious instructions hidden in the project files could be processed by the agent. * Ingestion points: Project files and documentation within the local codebase accessed during the interview process (referenced in SKILL.md). * Boundary markers: Not present. The skill lacks instructions to distinguish between data in the codebase and agent instructions. * Capability inventory: File system exploration and interactive dialogue with the user (instructed in SKILL.md). * Sanitization: Not present. The skill does not specify any filtering or validation for content read from the codebase.

grilling