skills/aws-samples/sample-well-architected-skills-and-steering/sustainability-optimization/Gen Agent Trust Hub
sustainability-optimization
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it is designed to analyze user-provided code packages and directories. Maliciously crafted data within these files could attempt to influence the agent's behavior during the assessment process.
- Ingestion points: The skill analyzes resource configurations, Dockerfiles, and CI/CD pipelines in Steps 2 through 6.
- Boundary markers: No specific delimiters or instructions to ignore embedded instructions within data files are provided.
- Capability inventory: The skill is restricted to analysis and reporting; it does not feature capabilities for command execution or external data transmission.
- Sanitization: There is no requirement in the instructions for validating or sanitizing the content of the analyzed files.
- [SAFE]: Fetches sustainability guidelines and framework questions from official AWS documentation repositories.
Audit Metadata