setup-git-hooks
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to configure the development environment, including
npm install,git config, andchmod +xto manage git hooks and formatter installations. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from repository files to drive its configuration logic, creating a surface for indirect prompt injection.
- Ingestion points: The agent reads
package.json, lockfiles (pnpm-lock.yaml,yarn.lock, etc.), and existing formatter configuration files (biome.json,.prettierrc) to determine project state and map language coverage (SKILL.md). - Boundary markers: No specific delimiters or safety instructions are used when evaluating content from these files.
- Capability inventory: The skill has the ability to write files, modify lifecycle scripts in
package.json, execute shell commands via the package manager, and perform git commits (SKILL.md). - Sanitization: There is no evidence of sanitization or validation of the data extracted from the repository files before it influences subsequent agent actions or configuration writes.
Audit Metadata