The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes content from several local files to generate its output, creating a potential surface for indirect prompt injection if the source files contain untrusted data.
Ingestion points: Data is loaded from .claude/skills/landing-pages/SKILL.md, .claude/skills/brand-voice/SKILL.md, and .claude/skills/icp/SKILL.md.
Boundary markers: The instructions do not include specific delimiters or warnings to ignore instructions that might be embedded within the context files.
Capability inventory: The skill has access to Read, Write, and Bash tools, which can be used to modify the filesystem or execute commands based on interpreted data.
Sanitization: There is no explicit requirement for the agent to sanitize or validate the content retrieved from external skill files before processing it.

sitelinks