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 in SKILL.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
Risk Level
SAFE
Analyzed
Sep 6, 2026, 08:55 AM
Security Audit — agent-trust-hub — email-drafter