The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to check for and read .claude/project-context.md or .cursor/project-context.md to identify content themes and audience requirements. This creates a surface for indirect prompt injection, as malicious instructions embedded within these project files could influence the agent's output. However, this is a primary function intended to provide tailored advice based on the user's project, and the skill does not possess sensitive capabilities such as network access or file system modifications that would escalate this risk.

resources-page-generator