infostealer-malware-detector
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes system commands for file discovery (find, Get-ChildItem), network interaction (curl), and malware remediation using platform-native tools like Windows Defender (MpCmdRun.exe) and ClamAV. These operations are core to the skill's stated purpose.\n- [EXTERNAL_DOWNLOADS]: Communicates with well-known security services (VirusTotal, MalwareBazaar) to retrieve reputation data for file hashes. It also provides references to official Microsoft security downloads for remediation.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the local file system and remote API responses, creating a theoretical surface for indirect prompt injection.\n
- Ingestion points: System-wide file paths/names and JSON payloads from VirusTotal API responses.\n
- Boundary markers: Absent; the instructions do not specify the use of delimiters for separating untrusted data from the prompt context.\n
- Capability inventory: File system write/delete permissions (quarantine/removal), network access, and execution of system binaries.\n
- Sanitization: Absent; the workflow relies on the agent's processing logic without explicit sanitization steps for external data.
Audit Metadata