review-testing
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill ingests untrusted source code for analysis. It lacks boundary markers to distinguish between code and embedded instructions and does not perform sanitization, creating a surface for indirect prompt injection.
- Ingestion points:
SKILL.md(input_schema: code-scope). - Boundary markers: Absent.
- Capability inventory: Restricted to text analysis and findings generation; no file system, network, or execution tools are requested.
- Sanitization: Absent.
- [EXTERNAL_DOWNLOADS]: The documentation specifies an installation command using the vendor's repository (
nesnilnehc/ai-cortex), which is the standard distribution mechanism for this author's skills.
Audit Metadata