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.mdto 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.pyin thescripts/directory. - Sanitization: None; data from the context file is interpolated directly into the drafting process.
- [COMMAND_EXECUTION]: The included script
scripts/sequence_analyzer.pyprovides 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