agent-native-audit
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external codebase content, such as README files, API service files, and tool definitions. This creates an inherent surface for indirect prompt injection where instructions embedded in the audited code could attempt to influence the agent's audit findings or subsequent recommendations.
- Ingestion points: Codebase files, documentation, and API definitions identified in
SKILL.mdandupstream-playbook.md(e.g., Step 2 in both files). - Boundary markers: No specific delimiters or instructions to ignore embedded commands are explicitly defined in the workflow steps.
- Capability inventory: The skill is configured to perform analysis and generate reports; it does not contain instructions for arbitrary code execution or external network operations beyond its stated purpose.
- Sanitization: No explicit sanitization or validation of the audited content is mentioned in the workflow.
Audit Metadata