project-status-report
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from various untrusted external sources, which could contain malicious instructions.
- Ingestion points: The skill explicitly processes meeting transcripts, Slack messages, emails, Google Docs via the
google_drive_fetchtool, and previous chat history viaconversation_search, as detailed inSKILL.mdandREADME.md. - Boundary markers: There are no explicit instructions for using delimiters or boundary markers to distinguish untrusted external data from system instructions.
- Capability inventory: The skill has the capability to write and update markdown files and save them directly into an Obsidian vault, which could be exploited if malicious instructions are successfully injected via the processed documents.
- Sanitization: The skill lacks technical sanitization (such as filtering or escaping) for external content, relying instead on high-level instructions to 'never invent information' and 'preserve original terminology'.
Audit Metadata