cobalt-strike-aggressor-development

Pass

Audited by Gen Agent Trust Hub on Nov 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a massive documentation repository for the Sleep programming language and Cobalt Strike Aggressor Scripting.
  • [EXTERNAL_DOWNLOADS]: The file references/sleep-functions/fetch_docs.py contains logic to fetch documentation from https://sleep.dashnine.org/manual/. This is the official source for Sleep documentation and is used here for documentation maintenance.
  • [PROMPT_INJECTION]: A static analysis flag was raised regarding references/aggressor-functions/beacon_job_hide_output.md for 'attempts to conceal actions'. This is a false positive; the file documents the beacon_job_hide_output function within Cobalt Strike, which allows operators to suppress job output in the tool's console. It is not an attempt to hide the AI agent's actions from the user.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes a large volume of documentation (627 files). While this represents a data ingestion surface, the content is purely technical documentation for programming and security tools, with no evidence of embedded malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 5, 2026, 06:22 PM