The Agent Skills Directory

[SAFE]: No malicious behavior, obfuscation, or unauthorized data access patterns were found. The skill follows best practices for document generation.
[INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it reads and processes external files and user input to generate reports. This is a standard risk for documentation skills. * Ingestion points: External files referenced via @file and user-provided tradeoff descriptions in SKILL.md. * Boundary markers: None explicitly mentioned in the instructions to the agent. * Capability inventory: Limited to searching for, reading, and writing local markdown files within the user's workspace. * Sanitization: No specific content sanitization is instructed beyond the output template structure.

portfolio-tradeoff