The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project data, such as the Art Bible (design/art/art-bible.md) and various asset directories, to derive the standards it uses for auditing. This represents an attack surface where maliciously crafted files in a repository could influence the diagnostic report.
Ingestion points: The skill reads design/art/art-bible.md and scans all files within the assets/ root and the code root.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded content within the files it reads.
Capability inventory: The skill is restricted to read-only tools including Read, Glob, Grep, and specific diagnostic Bash commands (stat, file, od, wc, du).
Sanitization: No explicit sanitization or validation of the content extracted from project files is performed before it is used to define audit parameters.

asset-audit