ntlm-relay-coercion

Pass

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references an external repository for the 'Coercer' automation tool located at https://github.com/p0dalirius/Coercer.
  • [COMMAND_EXECUTION]: The instructions include numerous command-line examples for executing network security tools such as Responder, ntlmrelayx.py, mitm6, PetitPotam.py, and certipy to perform authentication relay and coercion.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes workflows where the agent executes network tools and processes their output to determine the next steps in an attack chain.
  • Ingestion points: Data enters the agent's context through the output of commands like crackmapexec, ntlmrelayx, and coercer scan in SKILL.md and COERCION_METHODS.md.
  • Boundary markers: No specific boundary markers or instructions to ignore embedded content within tool outputs are present.
  • Capability inventory: The skill facilitates complex command execution through subprocess calls to external scripts.
  • Sanitization: There is no explicit sanitization of the data retrieved from external network targets before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 9, 2026, 12:00 PM