The Agent Skills Directory

[SAFE]: The skill operates as intended for UX strategy artifact generation. It utilizes a restricted set of tools (Read, Write, Glob, Grep) to process local files and generate markdown documentation. No evidence of prompt injection, data exfiltration, obfuscation, or unauthorized command execution was found.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection due to its processing of external project files, though the risk is negligible given the restricted toolset.
Ingestion points: Files located in analysis/, PRD/, and NOTES/ directories are ingested using the Glob and Read tools.
Boundary markers: The instructions do not specify the use of delimiters or safety instructions to isolate content read from these files.
Capability inventory: The skill's capabilities are limited to file system read/write and user interaction; it lacks the ability to execute shell commands or perform network operations.
Sanitization: The skill does not perform explicit sanitization of the content retrieved from analysis files before using it in the generation process.

ux-strategize