quality-check
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes various CLI tools and scripts based on the detected project environment (e.g.,
npm,mvn,pytest,cargo,dotnet). It also executes custom test scripts defined in the repository'sdocs/standards/testing.mdandscripts/arch/verify.*files. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from the repository, such as project manifests, testing standard documentation, and error logs from external tools.
- Ingestion points: The skill reads project configuration files (
package.json,pom.xml,pyproject.toml), testing standards (docs/standards/testing.md), and the output of executed test tools. - Boundary markers: No explicit delimiters or instructions are used to separate untrusted tool output or documentation content from the agent's internal reasoning.
- Capability inventory: The skill can execute shell commands for building and testing, write files to the local directory (reports and cache), and delegate code modifications to other agent skills.
- Sanitization: External content from test logs and documentation is interpolated into markdown reports without specific sanitization or escaping mechanisms.
Audit Metadata