pm-weekly-brief
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Slack messages, Google Calendar events, and Google Drive documents, which creates a surface for indirect prompt injection attacks.
- Ingestion points: Data is ingested from Slack mentions/DMs, Google Calendar events, and modified Google Drive documents as specified in the prompt template in
SKILL.md. - Boundary markers: The prompt template lacks explicit delimiters or instructions to the agent to ignore or isolate instructions that might be embedded within the retrieved messages or documents.
- Capability inventory: The agent is granted permissions to read private communications and write synthesized summaries back to the user's Google Drive.
- Sanitization: There are no instructions for the agent to sanitize, filter, or validate the content retrieved from external sources before processing it into the weekly brief.
Audit Metadata