email-sequence

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: No malicious patterns detected. The skill focuses on marketing workflows and providing educational templates for email automation.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits a surface for indirect instructions through its use of external context data.
  • Ingestion points: The skill reads from .claude/product-marketing-context.md to personalize generated email drafts.
  • Boundary markers: Absent; instructions do not explicitly warn the agent to ignore instructions embedded within the context file.
  • Capability inventory: The skill generates text artifacts (emails, strategies) and provides a local analysis script sequence_analyzer.py in the scripts/ directory.
  • Sanitization: None; data from the context file is interpolated directly into the drafting process.
  • [COMMAND_EXECUTION]: The included script scripts/sequence_analyzer.py provides local text-processing functionality. It evaluates word counts, CTA phrases, and spam triggers using regex. It does not access the network, read sensitive system files, or execute arbitrary commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 12:32 PM
Security Audit — agent-trust-hub — email-sequence