infra-cost
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Indirect Prompt Injection] (SAFE): The skill identifies multiple data ingestion points including
data/engineering/infra_costs.jsonanddata/cfo/latest_forecast.json. While boundary markers and sanitization are absent, the skill possesses no exploitable capabilities such as subprocess execution, network access, or file-writing tools, rendering the indirect injection surface non-viable for attack. - [Data Exposure & Exfiltration] (SAFE): The skill references sensitive business data (forecasts and infrastructure costs), but it lacks any network-enabled commands (e.g., curl, fetch) or tools to move this data outside the local environment.
- [No Code] (SAFE): No executable scripts (.py, .js, .sh), binary files, or package manager manifests (package.json, requirements.txt) are included in the skill definition.
- [Prompt Injection] (SAFE): Analysis of the instruction text reveals no attempts to bypass AI safety guardrails or override system instructions.
Audit Metadata