email-sequence

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and optimize user-provided email sequences, which creates an indirect prompt injection surface where malicious instructions could be embedded in the content being analyzed.
  • Ingestion points: The scripts/sequence_analyzer.py script and the instructions in SKILL.md process external email subjects and bodies provided by the user.
  • Boundary markers: The skill lacks explicit delimiters or instructions to the agent to disregard potential commands embedded within the emails it is optimizing.
  • Capability inventory: The analysis is performed by a local Python script and the agent's internal reasoning. The script is restricted to regex-based text analysis and does not have capabilities for network access, file system modification, or shell command execution.
  • Sanitization: There is no evidence of sanitization or filtering to detect or neutralize instructions hidden within the email marketing copy.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 05:04 AM
Security Audit — agent-trust-hub — email-sequence