xcpc-jiangly-style
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed entirely of markdown documentation and C++ code templates for competitive programming style guidance. No malicious code or hidden content was detected.
- [NO_CODE]: No executable scripts, binaries, or installation commands are present within the skill files.
- [PROMPT_INJECTION]: The skill uses instructional blocks like MANDATORY WORKFLOW and FINAL CHECKPOINT to maintain style consistency. These are well-defined behavioral constraints that do not involve safety bypasses or system prompt extraction.
- [DATA_EXFILTRATION]: The skill does not access sensitive local files or perform network requests.
- [EXTERNAL_DOWNLOADS]: No remote dependencies or external script downloads are requested by the skill.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied CP problems (ingestion points) and uses strict instructional checkpoints (boundary markers) to ensure style compliance. The skill possesses no capabilities for subprocess execution or network access (capability inventory), and primarily generates source code text (sanitization).
Audit Metadata