Gmail attachment download and Google Drive archival with gog.
65
82%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
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.
This skill’s workflow uses a Gmail “search/thread attachments” command and then downloads attachment files (i.e., content originating from external email authors), which can become LLM-readable text at runtime via `gog ... --download` output/processing; the prompt also flags attachments as “untrusted,” implying free-form outsider content is ingested for handling.
414e2ff
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.