test-coverage-improver
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands, specifically
bun run test:coverageandbun run check, to evaluate the repository and validate changes. - [DYNAMIC_EXECUTION]: The skill's core workflow involves generating new test scripts and executing them autonomously to measure coverage improvements. This creates a loop where generated code is run immediately in the local environment.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes repository source code and coverage artifacts (like HTML or JSON reports) to identify gaps. This represents a vulnerability surface where malicious instructions hidden in the source files or generated reports could influence the agent's autonomous behavior.
- Ingestion points: Repository source files, console output from test runners, and
coverage/artifacts. - Boundary markers: None identified; the skill processes the content directly to rank candidates.
- Capability inventory: File system write access (creating tests), file system read access, and shell command execution (
bun). - Sanitization: None identified for the ingested source or report data.
Audit Metadata