email-drafter
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown text and prompt templates. No executable scripts (Python, JavaScript, Bash), binaries, or external configuration files are included.
- [SAFE]: No malicious patterns, obfuscation, or data exfiltration vectors were identified. The skill's behavior is consistent with its stated purpose of drafting emails.
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates user-provided text into a prompt template, which is a standard pattern for this type of utility.
- Ingestion points: User input is interpolated into the
[DESCRIBE THE SITUATION, THE RECIPIENT, AND YOUR GOAL]variable inSKILL.md. - Boundary markers: Absent. User input is placed directly into the prompt template without delimiters.
- Capability inventory: No tools or command execution capabilities are defined or requested in the frontmatter or body.
- Sanitization: No specific sanitization or escaping is performed on the user input before interpolation.
Audit Metadata