skill-manager
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local shell scripts including setup.sh and export.sh to manage repository setup and bulk skill exports.
- [COMMAND_EXECUTION]: The skill utilizes the npx skills command-line tool to discover, validate, and add skill directories to the arsenal.
- [EXTERNAL_DOWNLOADS]: The workflow for external skills involves downloading content from remote GitHub repositories using the npx skills add command with arbitrary user/repo paths.
- [REMOTE_CODE_EXECUTION]: By guiding the agent to register community skills from external GitHub repositories, the skill establishes a path for fetching and integrating remote code into the agent's execution environment.
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface:
- Ingestion points: Community skills stored in the external/ directory sourced from GitHub.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined for the processing of external content.
- Capability inventory: Execution of shell scripts (setup.sh, export.sh), registration of code via npx skills, and file-writing capabilities to the gem/ directory.
- Sanitization: The skill does not describe any sanitization or validation steps for the content of external skills during extraction or synthesis.
Audit Metadata