The Agent Skills Directory

[SAFE]: No security risks or malicious patterns were identified. The skill's behavior is consistent with its intended use as a sales forecasting assistant.\n- [EXTERNAL_DOWNLOADS]: The skill uses WebFetch to retrieve documentation from the author's verified GitHub repository (github.com/sales-skills/sales). This is a legitimate feature for cross-skill discovery and does not involve the execution of untrusted code.\n- [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by ingesting remote markdown files. Ingestion point: WebFetch from the vendor's repository as described in SKILL.md. Boundary markers: Not explicitly specified for the fetched content. Capability inventory: The agent can Read local files, perform WebFetch, and provide advisory responses. Sanitization: Content is ingested as markdown. Given that the source is the vendor's own infrastructure, this design is considered a safe application of dynamic context injection for tool routing.

sales-forecast