The Agent Skills Directory

[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by incorporating data from project files into its workflow.
Ingestion points: Data is read from /docs/breakdown.md and /docs/bible.md to determine asset details and visual identity.
Boundary markers: No delimiters or isolation techniques are employed to separate content retrieved from these files from the agent's core instructions.
Capability inventory: The skill is authorized to read from and write to several project directories including /assets/ and /docs/, enabling it to modify registry and passport files.
Sanitization: There is no evidence of validation or sanitization of the content extracted from external project files before it is used for prompt interpolation.
[NO_CODE]: The skill consists entirely of markdown instructions and does not include any executable binary files or scripts.

asset-passport