Sales Outreach
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions contain no executable scripts, system commands, or external dependencies. It focuses purely on defining the persona and workflows for a sales agent.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data such as prospect research, LinkedIn activity, and email responses. This creates a potential surface for indirect prompt injection, though the risk is negligible as the skill lacks autonomous capabilities to perform dangerous actions.
- Ingestion points: Prospect data and external communication logs referenced in SKILL.md.
- Boundary markers: No delimiters or specific safety instructions are present to differentiate untrusted data from instructions.
- Capability inventory: Limited to generating outreach text; no shell, file, or network tools are utilized.
- Sanitization: No input validation or sanitization routines are specified.
Audit Metadata