cpp-concurrency-review
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (C++ source files, diffs, and design documents) to perform its review, which exposes the agent to potential indirect prompt injection attacks where instructions are hidden within code comments or string literals.
- Ingestion points: The skill ingests "files, diff, design, or data structure" supplied as review targets in
SKILL.md. - Boundary markers: The instructions do not define boundary markers or explicit prompts to ignore instructions found within the analyzed code content.
- Capability inventory: The skill requires read-only file access to perform deep logic analysis and generate structured reports.
- Sanitization: There are no instructions for sanitizing or filtering input content from the target files before processing.
Audit Metadata