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

sherlock

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the sherlock command-line tool to perform searches for usernames across hundreds of social networks.
  • [EXTERNAL_DOWNLOADS]: The documentation guides the user to install the sherlock-project package from the Python Package Index (PyPI), which is the official and well-known source for this tool, matching the author AeonDave.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies 'breach data' as a primary source of input for username hunting. This ingestion of untrusted external data, combined with the lack of defined boundary markers or sanitization logic in the instructions, creates a surface for indirect prompt injection where malicious input could attempt to influence the agent's command construction or logic. The skill relies on shell command execution as its primary capability.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 09:45 AM