code-explanation-generator
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied code snippets which could potentially contain hidden instructions designed to bypass agent constraints.
- Ingestion points: The skill uses
[paste code]placeholders across various templates (e.g., SKILL.md) to receive external code inputs. - Boundary markers: Inputs are wrapped in triple backticks within the prompt templates to provide basic separation between data and instructions.
- Capability inventory: The skill possesses no capabilities for command execution, network requests, or file system modifications.
- Sanitization: The skill does not implement specific sanitization or filtering logic for the code it processes.
Audit Metadata