cloud-native-readiness
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository files, creating a surface for indirect prompt injection attacks where malicious content in a project could attempt to influence the agent's assessment or subsequent actions.\n- Ingestion points: Assessment modules scan project source code and configuration files using shell utilities.\n- Boundary markers: Instructions in SKILL.md and modules/assess.md require explicit redaction of credentials and environment variables.\n- Capability inventory: The skill uses observation tools (grep, find, ls, wc) to analyze file patterns without executing project code.\n- Sanitization: The skill mandates summarizing findings and redacting sensitive data before generating the final report.
Audit Metadata