skills/immamdouhaboammar/antigravity-superpowers/agency-email-intelligence-engineer/Gen Agent Trust Hub
agency-email-intelligence-engineer
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and process raw email threads from external sources (Gmail, Outlook, MIME), creating an indirect prompt injection surface where malicious instructions embedded in emails could influence agent behavior.
- Ingestion points: The fetch_thread function in SKILL.md (lines 92-113) demonstrates fetching raw message content using imaplib.
- Boundary markers: The instructions do not specify the use of clear delimiters or 'ignore instructions' warnings when passing processed email content to the agent context.
- Capability inventory: The skill enables the agent to reconstruct thread topology and interface with frameworks such as LangChain and CrewAI.
- Sanitization: Although the skill mandates PII redaction, it lacks specific instructions for sanitizing or escaping natural language instructions contained within the email bodies.
Audit Metadata