install-anti-slop
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local installation script (
scripts/install.mjs) to copy plugin assets into the target repository. It also instructs the agent to run standard package manager commands (e.g.,npm view,npm install) and linting tools (e.g.,vp check). These actions are transparent and necessary for the skill's documented purpose. - [EXTERNAL_DOWNLOADS]: The skill references well-known packages (
oxlintand@oxlint/plugins) from the official npm registry. These are standard, reputable tools used in the JavaScript ecosystem. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the target repository, such as configuration files and
git statusoutput, to determine installation paths and versions. This creates an attack surface where malicious content in a repository could attempt to influence the agent's behavior. - Ingestion points:
SKILL.md(Step: "Choose the path") reads repository instructions andgit statusoutput. - Boundary markers: Absent.
- Capability inventory: File system modification via
scripts/install.mjs(cpSync) and dependency installation via package managers. - Sanitization: No explicit validation of the repository's metadata is performed before using it to influence installation parameters.
- [DYNAMIC_EXECUTION]: The skill provides TypeScript source code for Oxlint plugins. This code is intended to be vendored into the user's project and executed by the Oxlint engine during development and CI processes.
Audit Metadata