The Agent Skills Directory

[SAFE]: No malicious patterns such as command execution, data exfiltration, or obfuscation were detected. The skill follows best practices by verifying the existence of required input files and requesting user confirmation before performing file operations. It also encourages context management by suggesting a new session after completion.- [INDIRECT_PROMPT_INJECTION]: The skill has a potential attack surface for indirect prompt injection as it processes external documentation files, but the risk is assessed as safe due to the skill's limited capabilities and output format.
Ingestion points: The skill reads product documentation from docs/product/sense.md and HTML prototype files from the docs/product/demo/ directory.
Boundary markers: Absent; the skill relies on the integrity of the documentation provided in the project workspace.
Capability inventory: The skill is restricted to reading local text/HTML files, creating directories within the project structure, and writing a markdown report to docs/product/business-flow.md. It does not perform network operations or execute arbitrary system commands.
Sanitization: No explicit sanitization of input content is performed, but the resulting output is a non-executable markdown document.

product-business