The Agent Skills Directory

[SAFE]: The skill performs project context analysis by reading files from the standard user upload directory /mnt/user-data/uploads. This behavior is consistent with its stated purpose of enhancing prompts based on project structure.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes external, untrusted project data.
Ingestion points: Reads file content and project structure from /mnt/user-data/uploads (SKILL.md).
Boundary markers: The skill does not explicitly define markers or 'ignore' instructions for the content of the files it reads.
Capability inventory: The skill uses the view command for read access but does not include scripts that perform file-writing, network communication, or arbitrary command execution.
Sanitization: No sanitization or escaping of the ingested file content is performed before it is analyzed to build requirements.

prompt-enhancer