google-docs-md
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a utility guide for exporting Google Docs content. All operations described use standard command-line tools and official Google endpoints.
- [EXTERNAL_DOWNLOADS]: The skill uses
curlto fetch data fromdocs.google.com. As Google is a well-known and trusted service, this is documented as a safe operation. - [CREDENTIALS_UNSAFE]: References to
${TOKEN}are generic placeholders for authentication and do not contain hardcoded or leaked secrets. - [PROMPT_INJECTION]: Surface analysis for indirect injection: 1. Ingestion points: External Google Docs via native export (SKILL.md). 2. Boundary markers: None provided in snippets. 3. Capability inventory: curl, grep (SKILL.md). 4. Sanitization: None. This constitutes a potential surface for indirect prompt injection if the fetched content is later processed as instructions.
Audit Metadata