email-retention-sequences

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted user inputs such as product_name and target_audience which are interpolated directly into the prompt instructions without sanitization or boundaries.
  • Ingestion points: The product_name, target_audience, key_benefits, and churn_triggers inputs in SKILL.md enter the agent context.
  • Boundary markers: Absent. The skill does not use delimiters or explicit instructions to ignore potentially malicious embedded content within the user-provided inputs.
  • Capability inventory: The skill is limited to text generation and does not have access to subprocesses, file-writing, or network tools.
  • Sanitization: There is no evidence of filtering or escaping applied to user inputs before interpolation into the generation instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 04:37 PM
Security Audit — agent-trust-hub — email-retention-sequences