forge-type
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements logic for generating a CSS type scale (e.g., base, md, lg) using a base size and ratio. These values are retrieved from a local configuration file named
.forge.json. The operation is limited to text generation and mathematical computation without any network access, command execution, or sensitive data handling.- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from a local file (.forge.json). While this is an ingestion point for untrusted data, the instructions specify using the data for numeric calculations and CSS property generation, which carries minimal risk. There are no dangerous capabilities (like file writing or shell execution) triggered by this data. - Ingestion points: Contents of
.forge.jsonreferenced inSKILL.md. - Boundary markers: Absent; the skill expects the agent to parse the file for specific keys.
- Capability inventory: None detected. The skill only requests text output for the user.
- Sanitization: Absent; the skill relies on the agent's ability to interpret the JSON structure correctly.
Audit Metadata