cost-optimization
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions for analyzing cloud infrastructure costs and recommends actions for savings. It does not contain any malicious code, obfuscation, or exfiltration patterns.
- [SAFE]: Strong security guardrails are included, specifically instructing the agent to use ReadOnlyAccess IAM roles and to reject any prompts requesting the deletion of resources.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data such as cloud resource tags and billing reports which may be attacker-controlled. The risk is minimized as the skill's scope is strictly limited to generating reports and recommendations, and the instructions explicitly forbid resource modification.
- Ingestion points: Reads cloud provider metadata and billing exports (SKILL.md).
- Boundary markers: None identified.
- Capability inventory: No high-risk tools (file writing, shell execution, or outbound network calls) are defined or requested in the skill metadata or body.
- Sanitization: Not specified.
Audit Metadata