gmail-chrome
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection surface detected where untrusted external data can influence agent behavior.
- Ingestion points: Untrusted email subjects and body content are ingested into the agent context via chrome_take_snapshot in skill.md.
- Boundary markers: Absent; the skill does not utilize delimiters or specific instructions to isolate or ignore instructions embedded within the processed email content.
- Capability inventory: The skill has the capability to compose emails, send replies, and delete/archive messages using chrome_fill and chrome_press_key.
- Sanitization: No sanitization, filtering, or validation is performed on the data retrieved from the Gmail DOM before it is processed by the agent.
Audit Metadata