The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository's current files to populate documentation templates, creating a surface for indirect prompt injection.
Ingestion points: Files located in the repository root (e.g., README.md) and the /docs folder, along with user-provided text.
Boundary markers: There are no specific delimiters or instructions defined in the workflow or templates to isolate or ignore potentially malicious instructions within the ingested content.
Capability inventory: The skill employs filesystem tools like Write and Edit to create and update files in the /docs/product and /docs/tech directories.
Sanitization: There is no evidence of content sanitization or validation performed on the data read from the local files before it is used to generate documentation.

product-context-docs