oh-ut-generator
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by ingesting and processing external source code and existing test files to generate unit tests.\n
- Ingestion points: The skill instructs the agent to read and analyze C++ source files, header files, existing test files, and
BUILD.gnconfiguration files from the user's workspace.\n - Boundary markers: No specific delimiters or safety instructions (e.g., "ignore embedded instructions") are defined to isolate the ingested file content from the skill's own logic.\n
- Capability inventory: The skill allows the agent to create new C++ test files and append content to existing source and build files (
BUILD.gn).\n - Sanitization: The agent is not directed to sanitize or validate input files, allowing potentially malicious code in a source file to influence the agent's instructions during the generation process.
Audit Metadata