email-ops
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists solely of markdown instructions and does not include any scripts, binary files, or package dependencies.
- [PROMPT_INJECTION]: The skill involves processing untrusted external data from email threads, which constitutes a vulnerability surface for indirect prompt injection. 1. Ingestion points: External email thread content (SKILL.md). 2. Boundary markers: Absent; no specific instructions are provided to the agent to delimit or ignore instructions found within email bodies. 3. Capability inventory: Reading threads, creating drafts, archiving messages, and live-sending emails. 4. Sanitization: Absent; no sanitization or escaping of ingested email content is specified.
Audit Metadata