pm-weekly-brief

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from Slack messages, calendar event descriptions, and Google Drive documents.
  • Ingestion points: Reads Slack mentions/DMs, Google Calendar events, and modified Google Drive documents.
  • Boundary markers: None identified. The prompt does not use delimiters or instructions to ignore embedded commands within the retrieved text.
  • Capability inventory: The skill has read access to communication and file platforms and write access to Google Drive (via OUTPUT_FOLDER).
  • Sanitization: No evidence of sanitization or filtering of the retrieved content before it is processed for summarization.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 08:18 PM
Security Audit — agent-trust-hub — pm-weekly-brief