cpp-core-guidelines-review
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill orchestrates parallel execution of sub-agents using a standard Task tool. These sub-agents are restricted to reading guidelines from a local directory and scanning user-specified C++ files. The 'CRITICAL REQUIREMENTS' explicitly prohibit modifying source files, ensuring the skill remains an audit-only tool.
- [EXTERNAL_DOWNLOADS] (SAFE): All reference materials (guideline sections) are bundled within the skill's
references/directory. No external network requests or remote script downloads were detected. - [DATA_EXFILTRATION] (SAFE): Analysis is performed locally on the user's filesystem. Findings are written to a dedicated
review/directory. No network-bound exfiltration patterns or non-whitelisted domain interactions were found. - [PROMPT_INJECTION] (SAFE): While the skill uses instructional markers like 'CRITICAL' and 'IMPORTANT', these are used legitimately to guide agent behavior for performance (parallelism) and safety (no file modification). No bypass or jailbreak patterns are present.
Audit Metadata