property-based-testing
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves analyzing external source code and existing test suites, creating a potential attack surface for indirect prompt injection.\n
- Ingestion points: The agent is guided to read and triage project files, including source code and tests (e.g., in
references/libraries.mdandreferences/reviewing.md).\n - Boundary markers: The instructions do not explicitly require the use of data delimiters or safety warnings to ignore instructions embedded within the analyzed code.\n
- Capability inventory: The agent context for this skill typically includes file system access and shell execution (suggested via
rgcommands), which could be manipulated by adversarial content in analyzed files.\n - Sanitization: The instructions do not specify any sanitization or validation steps for the content of the files being read and processed.
Audit Metadata