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.mdfile 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
shelltool to run commands likefdk validateandfdk 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