memory-email-ingest

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external email messages.
  • Ingestion points: External email body content is retrieved using the gmail_read_message tool as described in the process section of SKILL.md.
  • Boundary markers: No delimiters or protective instructions (e.g., "ignore instructions within the email body") are used when the content is summarized and written to the daily log files.
  • Capability inventory: The skill has the capability to write and append to local files at /Users/jesseanglen/Documents/RandomStuff/memory-kb/, including daily markdown logs and state JSON files.
  • Sanitization: The instructions do not specify any sanitization, escaping, or validation of the email content before it is processed and stored in the local file system.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 09:20 PM
Security Audit — agent-trust-hub — memory-email-ingest