context-engineering

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (HIGH): Encourages installing unverified global packages (linearis) and running code via npx from an untrusted GitHub repository (justgetAI/agent-skills).
  • [PROMPT_INJECTION] (HIGH): The skill is vulnerable to Indirect Prompt Injection. Agents process untrusted project files and have the capability to execute shell commands, perform git operations, and write to the filesystem, creating a significant attack surface.
  • [COMMAND_EXECUTION] (HIGH): The skill makes extensive use of shell scripts (init.sh), git commands, and Task primitives to manage codebase state and coordinate swarms.
  • [REMOTE_CODE_EXECUTION] (HIGH): Recommends execution of remote scripts from unverified sources through npx, which lacks source integrity verification.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 01:26 PM