lefthook
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and analyze untrusted data from a user's repository (e.g., existing
lefthook.ymlfiles,package.json,Gemfile, and other manifests) to generate or update configurations. - Ingestion points: The skill reads repository configuration files and project manifests (
lefthook.yml,package.json,Gemfile, etc.) to determine the existing toolchain and configurations. - Boundary markers: There are no explicit instructions to the agent to disregard instructions embedded in the analyzed files.
- Capability inventory: The skill can author new configuration files and recommends the execution of shell commands through the Lefthook CLI (e.g.,
lefthook install,lefthook run). - Sanitization: There is no mention of sanitizing or escaping the content read from the repository before it is processed by the agent.
Audit Metadata