thesis-workspace-init
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a Python script (
scripts/run.py) that performs local file system operations usingpathlib. It creates directories and writes markdown templates. These operations are limited to the workspace path provided via command-line arguments and are consistent with the skill's stated purpose of initializing a project structure. - [DATA_EXFILTRATION]: There are no network operations (e.g., curl, requests) or attempts to access sensitive system files (e.g., SSH keys, environment variables). The script only checks for the existence of LaTeX-related project files like
main.texandchapters/. - [INDIRECT_PROMPT_INJECTION]: While the skill interacts with a user-provided workspace directory, it does not ingest untrusted data from external sources into the agent prompt in a way that could lead to injection. It strictly creates pre-defined folder structures and boilerplate text files.
- [METADATA_POISONING]: The YAML frontmatter and README files contain standard project descriptions and triggers. No deceptive or malicious instructions were found in the metadata fields.
Audit Metadata