disk-forensics
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted disk images and forensic data which could contain malicious metadata (like crafted filenames or timestamps) intended to influence the agent's analysis.
- Ingestion points: Disk image files (e.g., .E01, .dd) and raw block devices (e.g., /dev/sdb) accessed via DiskAnalyzer.
- Boundary markers: None present in the skill documentation.
- Capability inventory: File system parsing, file recovery (writing to /evidence/), MFT analysis, and partition enumeration.
- Sanitization: No explicit sanitization of extracted file metadata or strings is documented.
Audit Metadata