email-sequence
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown documentation, guidelines, and templates. There are no executable scripts (Python, JavaScript, etc.), shell commands, or external package dependencies identified in any of the provided files.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions in
SKILL.mddirect the agent to incorporate data fromMEMORY.mdandUSER.mdinto its output. While this creates an ingestion surface for untrusted data, the skill possesses no dangerous capabilities—such as network access, file modification, or command execution—to facilitate exploitation. This represents a standard instructional pattern for contextual agents.
Audit Metadata