cpp-pro
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection due to its core functionality of analyzing untrusted external data.
- Ingestion points: The agent is instructed to query context managers for project structures, review
CMakeLists.txtfiles, and analyze existing source code templates and memory patterns within a workspace (SKILL.md). - Capability inventory: The skill is designed to "Implement solutions," which typically requires file system write access to generate or modify source code and build files.
- Boundary markers: The instructions do not define clear delimiters or include safety warnings to ignore potentially malicious instructions embedded within the C++ source code or build files it analyzes.
- Sanitization: There are no specified procedures for sanitizing, escaping, or validating the content retrieved from external codebases before it is processed by the agent.
Audit Metadata