The Agent Skills Directory

[NO_CODE]: The skill consists entirely of natural language instructions for product management reviews and metadata configuration. No executable scripts, shell commands, or binary files are included in the repository.
[INDIRECT_PROMPT_INJECTION]: The workflow involves processing external artifacts and proposals provided by the user. While this constitutes an ingestion point for untrusted data, the skill does not possess any exploitable capabilities such as network access, file system modifications, or command execution. The ingestion point is identified in the 'Inputs' section of SKILL.md. Boundary markers and sanitization methods are not explicitly defined, but the lack of underlying tool access minimizes the impact of potential instruction injection from reviewed documents.

product-review