ai-engineer
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines an indirect prompt injection surface.
- Ingestion points: Document processing and web scraping are identified as ingestion points (referenced in
SKILL.md). - Boundary markers: No explicit delimiters are defined for untrusted data.
- Capability inventory: Capabilities include tool integration for web search and code execution (referenced in
SKILL.md). - Sanitization: The skill provides safety instructions for guardrails and jailbreak detection (referenced in
SKILL.md).
Audit Metadata