freshworks-publish-skill

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The SKILL.md file contains instructions for autonomous execution, explicitly directing the agent to 'IMMEDIATELY execute without asking permission' and 'DO NOT: Ask for confirmation before running commands'. This overrides the typical user-in-the-loop safety model.
  • [COMMAND_EXECUTION]: The skill employs the shell tool to run commands like fdk validate and fdk pack. The combination of autonomous execution instructions and shell access creates a risk profile where commands are run on the local system without explicit user verification for each step.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 01:34 PM