setup-amit-skills
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes existing repository configuration files such as AGENTS.md, CLAUDE.md, and CONTEXT.md to provide configuration recommendations. This creates a surface where instructions embedded in these files could influence the agent's behavior during the setup process.
- Ingestion points: SKILL.md performs discovery of agent instruction files, context docs, and ADR layouts across the repository.
- Boundary markers: The skill logic specifies appending content to clearly marked sections and preserving existing user prose, which helps maintain separation.
- Capability inventory: The skill utilizes git remote -v for environment discovery and has the capability to write or update multiple markdown files within the repository.
- Sanitization: The workflow incorporates a mandatory human-in-the-loop confirmation step before any changes are written, requiring the user to review drafts and explicitly confirm modifications.
- [EXTERNAL_DOWNLOADS]: The skill documentation refers to the skills CLI provided by Vercel Labs for installation and points to the author's GitHub repository for the skill source content.
Audit Metadata