skill-creator
Warn
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides procedures for fetching content from user-specified URLs using tools like
curlorweb-fetchto install new skills. - [REMOTE_CODE_EXECUTION]: The installation guide for remote skills directs the agent to execute setup instructions, such as downloading scripts or binary files, defined within the fetched content.
- [COMMAND_EXECUTION]: Procedural instructions for skill installation require the agent to run arbitrary shell commands found in third-party skill definitions to complete setup.
- [PROMPT_INJECTION]: The process of ingesting and following instructions from externally sourced files creates a surface for indirect prompt injection.
- Ingestion points: Content fetched from user-provided URLs (processed in
SKILL.md). - Boundary markers: Absent; the agent is directed to follow the instructions within the saved file directly.
- Capability inventory: The skill utilizes
bash,read,write, andedittools as specified inSKILL.md. - Sanitization: No sanitization or validation of the remote content is performed before processing.
Audit Metadata