init-prettier-git-hooks
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute multiple shell commands, including
pnpm addfor dependency installation,simple-git-hooksfor modifying Git hook files in the.gitdirectory, andgit add --renormalizefor modifying the Git index. While the skill mandates user authorization for these actions, they involve significant changes to the local environment. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the project being analyzed, which could contain instructions designed to influence the agent's behavior.
- Ingestion points: Reads
package.json, lockfiles, and various Prettier and Git configuration files (.prettierrc,.editorconfig,.gitattributes) from the target project root. - Boundary markers: The instructions do not define clear delimiters or "ignore instructions" directives when reading these external files.
- Capability inventory: The skill can install arbitrary Node.js packages, write configuration files, modify Git hooks, and stage files in the repository.
- Sanitization: No explicit sanitization or validation of the project files' content is performed before the data is processed by the AI.
Audit Metadata