qt-cpp-bug-fixer
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has a workflow that requires the agent to ingest and analyze untrusted external data, which could contain malicious instructions.
- Ingestion points: The skill instructions (Diagnostic Phase) direct the agent to read source code, compiler errors, and runtime backtraces from the user's project environment.
- Boundary markers: The skill does not provide or require the use of boundary markers (e.g., XML tags or unique delimiters) when interpolating this untrusted data into the prompt context, nor does it instruct the agent to ignore instructions found within the code or logs.
- Capability inventory: The skill workflow involves locating and modifying code files based on external input, implying capabilities for file system read and write operations.
- Sanitization: There are no requirements to sanitize, filter, or escape the external content before the agent processes it.
Audit Metadata