skill-creator
Pass
Audited by Gen Agent Trust Hub on May 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions in
SKILL.mdguide the agent to fetch content from arbitrary remote URLs usingcurlorweb_fetchduring the installation process. - [COMMAND_EXECUTION]: The skill includes Python scripts (
scripts/init_skill.py,scripts/package_skill.py) that perform file system management, including creating directories, writing files, and modifying file permissions (chmod 755). - [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by design, as it instructs the agent to ingest and follow instructions from external sources such as remote URLs and
INSTALL.mdfiles. - Ingestion points: Remote URLs and external skill directories in
SKILL.md. - Boundary markers: Absent; the skill does not use specific delimiters or warnings to isolate instructions found in external skill packages.
- Capability inventory: Includes
bash,read,write,edittools, and the execution of Python scripts for workspace management. - Sanitization: None; the skill does not validate or sanitize instructions contained within downloaded installation files.
Audit Metadata