Ae1
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - [mb-text-workflow](SKILL.md) — For text-based projects
Security audit
Security checks for vulnerabilities and agentic risk
This skill creates a project-local memory-bank documentation folder and includes a git commit step, which is disclosed and purpose-aligned but should be reviewed before use.
Install only if you want an agent to create a memory-bank documentation structure in a project. Before running it, confirm the absolute project root, review the files it plans to create, and treat the git commit step as optional until you have inspected the generated documentation.
Referenced artifact was not completely inspected
- [mb-text-workflow](SKILL.md) — For text-based projects
Referenced artifact was not completely inspected
- [mb-text-workflow](SKILL.md) — For text-based projects
The skill explicitly instructs running git add and git commit, which mutates repository history in addition to creating local documentation files. In an agent context, version-control writes are a higher-risk side effect because they can persist unintended changes, trigger downstream automation, and make rollback harder if performed without an explicit user confirmation step.
The skill directs creation of directories and files in the target project but does not prominently warn that it will modify the filesystem and may later alter git history. In a normal human-run setup this is expected behavior for an initialization tool, but for an autonomous agent this omission increases the chance of unexpected writes in the wrong project root or repository.