configure-tests
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
Bashto perform environment discovery usingfindandgrepto identify project configuration files and test directories. It also invokes package managers (npm,uv,cargo) to install testing dependencies. - [EXTERNAL_DOWNLOADS]: The skill retrieves version information from official project websites and installs standard testing libraries (e.g., Vitest, Jest, pytest, cargo-nextest) from trusted registries (npm, PyPI, Crates.io). All external URLs and resources belong to well-known technology organizations.
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes file contents from the project directory to guide its configuration actions.
- Ingestion points: reads from
package.json,pyproject.toml,Cargo.toml, and identified test configuration files. - Boundary markers: no explicit delimiters or instructions to ignore embedded content are used during file ingestion.
- Capability inventory: includes file modification (
Write,Edit) and system command execution (Bash). - Sanitization: no explicit sanitization or validation of the ingested file contents is performed before processing.
Audit Metadata