email-drafting
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists exclusively of markdown documentation and natural language prompt templates. It does not include any Python scripts, Node.js packages, shell commands, or other executable components.
- [PROMPT_INJECTION]: The skill acts as a template for processing untrusted user input (recipient details, purpose, key points). It lacks specific boundary markers or delimiters to isolate this data from the underlying instructions, which is a common characteristic of prompt-based skills. However, because the skill has no access to tools, the file system, or the network, the impact of any potential indirect prompt injection is limited to the content of the generated email.
- Ingestion points: User-provided fields in SKILL.md (Usage section).
- Boundary markers: Not present.
- Capability inventory: None (the skill lacks code or allowed-tools configuration).
- Sanitization: Not present.
Audit Metadata