concurrency
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface (Category 8) due to its core function of processing untrusted content from user tasks.\n
- Ingestion points: As shown in
references/GUIDE.md, the skill ingests user-supplied task descriptions and C++ code for analysis.\n - Boundary markers: The skill's instructions do not include delimiters or specific guidance to prevent the agent from executing instructions potentially embedded within the user's code.\n
- Capability inventory: The skill is designed for development and refers to system-level debugging tools like
gdbinSKILL.md, which involves shell and file system interactions.\n - Sanitization: No sanitization or escaping of external content is specified in the skill's operational flow.
Audit Metadata