workflow-automation

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill documents workflows that ingest data from untrusted external sources, such as RSS feeds, GitHub pull requests, and customer support tickets. This represents a standard surface for potential indirect prompt injection attacks. * Ingestion points: The documentation describes fetching data from NewsAPI, GitHub, and incoming support tickets (SKILL.md). * Boundary markers: The provided code snippets do not include explicit delimiters or safety instructions to separate untrusted data from agent commands. * Capability inventory: The skill utilizes Python execution and interacts with third-party APIs (GitHub, Slack, Zendesk) (SKILL.md). * Sanitization: While the example code lacks explicit sanitization, the documentation recommends PII redaction and human-in-the-loop approvals as security best practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 07:53 PM
Security Audit — agent-trust-hub — workflow-automation