lov-writing-style
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to run local Python scripts (
style_audit.pyandprofile_store.py) included in the skill package. These scripts perform writing style analysis and manage local configuration settings respectively. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided drafts and notes which could contain malicious instructions. The skill instructions include specific workflow steps to isolate user data from agent commands and utilize external quality gates to validate content before final output.
- [EXTERNAL_DOWNLOADS]: The skill documentation describes an installation process that fetches content from a remote repository (
lovstudio/writing-style-skill) using a command-line utility (npx skills). This is an expected behavior for the skill's deployment model and corresponds to the skill author's own repository. - [DATA_EXFILTRATION]: The
profile_store.pyscript implements a data validation check to prevent the storage of sensitive information such as API keys and tokens in the local profile store, mitigating accidental credential exposure.
Audit Metadata