Suspicious Email Analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted content from external emails, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: The skill prompts the user to provide sensitive email data including the sender address, subject line, full email body, and links for analysis (SKILL.md).
- Boundary markers: The instructions define a clear output format for the assessment report but do not establish strict boundary markers or delimiters for the ingested email content to prevent it from being interpreted as instructions by the agent.
- Capability inventory: The skill is limited to text analysis and report generation; no scripts, subprocess calls, file-system modifications, or network operations were detected in the provided file.
- Sanitization: The skill provides guidelines for human safety (e.g., "do NOT click any links") but does not implement automated sanitization or filtering of the input text to neutralize potential injection payloads.
Audit Metadata