The Agent Skills Directory

[SAFE]: The skill's primary function is to provide architectural guidance for data enrichment. It includes a local Python script, scripts/check-output.py, which is a benign utility for validating that generated deliverables contain the necessary markdown headers. The script only performs local file reads on paths provided by the agent and contains no network or persistence logic.
[INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting user-provided data specifications (CRM fields, identity fields). This constitutes a standard attack surface for indirect prompt injection; however, the skill is focused on design and documentation rather than automated execution. There are no exploitable capabilities such as arbitrary network requests or file writes that could be leveraged by a malicious payload in the source data.

api-enrichment