ue5-architecture
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection through its module indexing utility script.
- Ingestion points:
scripts/generate_module_index_v2.pyscans and reads file names from local directories specified via environment variables or host paths. - Boundary markers: Absent; the script does not use specific delimiters to separate untrusted filesystem metadata from its logic.
- Capability inventory: The script has file-write access to the
references/directory within the skill folder. - Sanitization: Absent; the script uses regular expressions to extract module names but does not validate them against malicious content before writing to index files.
Audit Metadata