salesloft-hello-world

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides legitimate code examples for the SalesLoft REST API v2 (https://api.salesloft.com/v2/). It correctly instructs users to handle secrets via environment variables (SALESLOFT_API_KEY) and references official developer documentation.
  • [INDIRECT_PROMPT_INJECTION]: The skill demonstrates how to ingest data from external SalesLoft API endpoints. While this is the intended primary functionality, it represents a standard indirect prompt injection surface where maliciously crafted data within the external SalesLoft account could attempt to influence the agent's behavior.
  • Ingestion points: Data retrieved via api.get('/people.json') and api.get('/cadences.json') in the code snippets provided in SKILL.md.
  • Boundary markers: None are present in the example code to delimit external data from agent instructions.
  • Capability inventory: The skill frontmatter configures access to Read, Write, Edit, and Bash tools.
  • Sanitization: The example code does not include validation or sanitization of the data returned from the API.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 03:01 PM
Security Audit — agent-trust-hub — salesloft-hello-world