memory-bubbles-ingest

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted content from external emails and appends it to local files without sufficient isolation.
  • Ingestion points: Meeting summaries, action items, and transcripts fetched from Gmail messages using the gmail_read_message tool.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to prevent the agent from acting on malicious commands hidden within the email body.
  • Capability inventory: The skill has the capability to read from and write to the local file system (e.g., /Users/jesseanglen/Documents/RandomStuff/memory-kb/daily/).
  • Sanitization: No sanitization or verification steps are defined for the data extracted from the email before it is written to local storage.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 05:03 AM
Security Audit — agent-trust-hub — memory-bubbles-ingest