skills/aeondave/malskill/snaffler/Gen Agent Trust Hub

snaffler

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the official SnaffCon GitHub repository for downloading the Snaffler executable.- [COMMAND_EXECUTION]: The skill provides PowerShell snippets for running Snaffler.exe with various flags to audit file shares and local directories.- [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface by processing data from untrusted network shares and local files which could contain malicious instructions.
  • Ingestion points: File content and metadata read by Snaffler.exe from targets specified by the -n or -i flags.
  • Boundary markers: None specified in the instructions for isolating ingested content from the agent's logic.
  • Capability inventory: The tool can execute file system reads, write logs to disk, and copy matching files to a local directory.
  • Sanitization: No automated content filtering is described, though manual redaction of sensitive evidence is advised in the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 09:45 AM