code-generator
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection. It is designed to ingest and process user-provided specifications and requirements to generate executable code, which could be manipulated if those inputs contain hidden instructions.
- Ingestion points: Untrusted data enters the agent context through the 'specification' and 'requirements' JSON fields defined in the SKILL.md input requirements.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat input as data rather than instructions, nor are there warnings to ignore embedded commands.
- Capability inventory: The skill facilitates code generation and implementation of logic across multiple programming languages and frameworks.
- Sanitization: The skill does not define any input validation or sanitization logic to filter out prompt injection patterns within the specifications.
Audit Metadata