cpp
Pass
Audited by Gen Agent Trust Hub on Feb 13, 2026
Risk Level: LOW
Full Analysis
- SAFE (SAFE): A thorough audit of the SKILL.md and examples.md files indicates that the skill follows standard agent protocols for information retrieval and report generation. No malicious patterns, such as hardcoded credentials, obfuscation, or unauthorized file access, were detected.
- PROMPT_INJECTION (LOW): The skill possesses an ingestion surface for user-controlled data via project files and prompts. However, because the skill's capabilities are limited to generating textual advice and saving markdown reports to a designated directory, there is no viable path for an injection to result in harmful system side effects.
- DATA_EXPOSURE (INFO): The skill accesses project-specific memory (e.g., project_overview.md) to provide context-aware C++ guidance. This behavior is consistent with the stated purpose of the skill and does not involve the retrieval of sensitive system configuration or private user data.
Audit Metadata