fuzz
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because its core functionality involves ingesting and analyzing external source code to determine test parameters.
- Ingestion points: The skill reads application source code files, including API handlers, file parsers, and CLI argument parsers, to identify validation logic and constraints as described in the 'Identify Input Handlers' section.
- Boundary markers: The instructions do not specify the use of delimiters or protective framing (e.g., 'ignore embedded instructions') when processing the content of these external files.
- Capability inventory: The skill utilizes file-reading capabilities to analyze project code and file-writing capabilities to output generated test case sets into the
.appsec/fuzz/directory. - Sanitization: The workflow lacks steps to sanitize, escape, or validate the content of the analyzed source code files before they are interpreted by the agent to generate test inputs.
Audit Metadata