The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill represents an indirect prompt injection attack surface as it processes external files, but it lacks dangerous capabilities.
Ingestion points: Analyzes component implementation and documentation examples located at $ARGUMENTS in SKILL.md.
Boundary markers: Absent.
Capability inventory: Limited to read-only capabilities via Read, Grep, and Glob tools specified in the frontmatter of SKILL.md.
Sanitization: Absent.
Context: Because the capability inventory is strictly limited to reading content and does not permit network connections, file modifications, or command execution, the risk is negligible.

a11y-audit