aws-cost-operations
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill functions by ingesting and analyzing data from external AWS sources, which inherently creates a surface for indirect prompt injection.
- Ingestion points: The skill fetches data through various MCP tools, such as
mcp__aws-mcp__aws___search_documentationfor searching AWS docs and various monitoring tools that retrieve CloudWatch logs, CloudTrail API activity, and billing metrics inSKILL.md. - Boundary markers: The instructions lack explicit delimiters or specific instructions for the agent to treat information retrieved from these external tools as untrusted content.
- Capability inventory: The skill instructions across all files (
SKILL.md,operations-patterns.md,cloudwatch-alarms.md) demonstrate high-tier capabilities, including the ability to analyze billing, estimate costs, monitor infrastructure, and perform security assessments. - Sanitization: No evidence of sanitization, filtering, or validation of the data retrieved from external AWS APIs was found in the skill's instructions.
Audit Metadata