mapping-mitre-attack-techniques
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches the authoritative MITRE ATT&CK Enterprise STIX data bundle from the official MITRE GitHub repository.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests and processes external datasets to generate reports and heatmap layers. * Ingestion points: The
scripts/agent.pyscript reads data fromenterprise-attack.jsonand a user-provideddetection_rules.json. * Boundary markers: There are no explicit delimiters or 'ignore instructions' warnings implemented in the data ingestion logic. * Capability inventory: The script performs file system read and write operations to load datasets and export Navigator layers. * Sanitization: The skill relies on standard JSON parsing and the officialmitreattack-pythonlibrary for structured data handling.
Audit Metadata