The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and modify Symfony project architectures, which involves reading untrusted project files. This creates a surface for indirect prompt injection where malicious instructions embedded in codebase comments or strings could influence the agent's behavior.
Ingestion points: Project files accessed via the Read, Glob, and Grep tools during the architectural boundary establishment phase.
Boundary markers: None identified; the skill does not explicitly instruct the agent to ignore or delimit instructions found within the processed code.
Capability inventory: The skill is restricted by the platform to Read, Glob, and Grep capabilities. It lacks file-writing or shell execution permissions, significantly limiting the potential impact of an injection attack.
Sanitization: No specific sanitization or validation of the content read from the filesystem is described.

interfaces-and-autowiring