The Agent Skills Directory

[SAFE]: No malicious behavior or high-risk security patterns were identified. The skill's functionality is consistent with its stated purpose of gathering external context from the web.
[PROMPT_INJECTION]: The skill contains an indirect prompt injection surface, which is inherent to any tool that processes untrusted data from the internet. * Ingestion points: Data is retrieved from external websites via WebSearch and WebFetch tools (referenced in SKILL.md). * Boundary markers: Absent; there are no specific delimiters defined to isolate fetched content from agent instructions. * Capability inventory: The skill utilizes the Task tool to invoke subagents (oh-my-claudecode:document-specialist) which possess network access capabilities. * Sanitization: No sanitization or filtering logic is present in the synthesis protocol. Despite this surface, no malicious intent was detected, and the risk level is consistent with standard web-browsing agent capabilities.

external-context