ai-engineer
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [SAFE]: No malicious patterns detected. The skill provides architectural guidelines and behavioral instructions for an AI Engineering role, emphasizing reliability and safety controls.
- [INDIRECT_PROMPT_INJECTION]: The skill acknowledges an attack surface via untrusted data ingestion (web scraping, PDF extraction). Ingestion points: Documented in
SKILL.md. Boundary markers: Present; instructions mandate adding guardrails for prompt injection. Capability inventory: Mentions tool integration for code execution and API calls. Sanitization: Present; mandates PII detection and content moderation. - [DYNAMIC_EXECUTION]: Mentions code execution and tool use as standard components of agent frameworks, not as instructions for immediate unsafe local execution.
Audit Metadata