The Agent Skills Directory

[SAFE]: The skill instructions consist entirely of markdown-formatted logic, tables, and playbooks. No indicators of prompt injection, data exfiltration, or malicious intent were found.
[INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing user-supplied data such as call transcripts, account lists, and deal descriptions to generate recommendations. This is an intended functional surface and lacks the dangerous capabilities required for exploitation.
Ingestion points: Diagnostic questions in SKILL.md rely on processing user-provided goals, transcripts, and account data.
Boundary markers: Absent; the skill operates as a high-level reasoning framework.
Capability inventory: None. The skill does not possess file system access, network capabilities, or shell execution tools.
Sanitization: Not applicable as the skill's output is limited to advisory recommendations for other tool usage.

sales-orchestrator