outreach-writer-free
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill ingests untrusted lead profile data such as company names and trigger events which are interpolated into the prompt, creating a surface for indirect prompt injection. \n
- Ingestion points: Lead profile inputs (company, prospect name, title, trigger event) defined in
SKILL.md. \n - Boundary markers: Absent; the instructions do not use specific delimiters or instructions to the agent to disregard potential commands embedded within the lead profile data. \n
- Capability inventory: The skill is designed for text generation and does not explicitly utilize tools for file system access, shell execution, or network communication. \n
- Sanitization: Absent; no explicit validation or escaping of user-provided content is implemented to neutralize potential injection attempts.
Audit Metadata