The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified in the skill instructions or logic. The skill adheres to its stated purpose of providing a strategic framework for entrepreneurs.
[PROMPT_INJECTION]: The skill utilizes WebSearch and WebFetch to gather information from external websites, creating an architectural surface for indirect prompt injection. This is a functional requirement for its research-based purpose and is assessed as safe given the lack of dangerous capabilities. * Ingestion points: External competitor websites, reviews, and community forums (SKILL.md). * Boundary markers: None explicitly present to separate external content from internal instructions. * Capability inventory: The skill is limited to generating strategic advice and output reports; no dangerous capabilities like shell execution or file system modifications are involved. * Sanitization: The content retrieved from the web is not specified to be sanitized or filtered before analysis.

gtm-strategy