yao-skill-manager
Pass
Audited by Gen Agent Trust Hub on May 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local shell scripts
./setup.shand./export.shto register or export skills globally within the environment. - [EXTERNAL_DOWNLOADS]: The instructions mandate the use of
npx skills add <repo_path>to download and inspect community skills from external repositories. - [REMOTE_CODE_EXECUTION]: The use of
npxto fetch and install skills from remote GitHub paths (e.g.,npx skills add <user>/<repo>/...) can lead to remote code execution if the target repository contains malicious logic. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data by downloading and organizing community skills into the
external/directory. - Ingestion points: The
external/directory where community skills are archived and the output ofnpx skills addcommands. - Boundary markers: None present; the agent is not instructed to use delimiters or ignore instructions found within external skills.
- Capability inventory: The skill allows execution of shell scripts (
./setup.sh), file system modifications (gem/<category-name>.txt), and Git operations (commit,push). - Sanitization: No sanitization or validation of the content of external skills is mentioned before they are registered or documented.
Audit Metadata