Synthesize durable KTX wiki pages from staged Google Drive document pulls. Load when a WorkUnit contains Google Doc raw files from `docs/**`.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow ingests Google Drive doc text from `page.md`/`rawFiles` in the WorkUnit (step 1–2 via `read_raw_file`/`read_raw_span`), so an outsider who can submit/upload those Google Docs into the workflow’s input path can inject arbitrary free text that the LLM will read and synthesize.
49a4ae6
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.