project-status-report
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill processes untrusted external data such as meeting transcripts and Google Drive documents, creating an attack surface for indirect prompt injection.\n- Ingestion points: Data enters the agent via the
google_drive_fetchandconversation_searchtools, as well as via user-provided local file paths for an Obsidian vault as described inSKILL.mdandcommands/pm.memory.md.\n- Boundary markers: Absent; the instructions do not implement explicit delimiters or system-level warnings to isolate untrusted data from the core operating instructions.\n- Capability inventory: The skill can search, fetch, and update/write markdown files using agent tools and vault access.\n- Sanitization: Absent; there is no logic defined for the validation or sanitization of ingested content before it is processed into reports.
Audit Metadata