The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or dangerous execution capabilities were detected in this skill. Its behavior is limited to text generation for sales coaching purposes.
[INDIRECT_PROMPT_INJECTION]: The skill attempts to read context from a local project file .agents/sales-context.md to tailor its recommendations. While this represents a data ingestion surface, the skill has no dangerous capabilities (like code execution or network access) that could be exploited via malicious content in that file. This is a standard pattern for providing context to the agent.

discovery-call