ai-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute standard development utilities such as linters (e.g.,
eslint,phpcs,stylelint), type checkers (e.g.,phpstan,mypy), and unit test suites. These commands are executed within the local project environment to validate code quality as part of the primary review function. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze external code changes, such as pull requests and diffs, which represents an ingestion surface for untrusted data.
- Ingestion points: The agent reads and analyzes external code files and diff content (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions embedded within the code being reviewed.
- Capability inventory: The agent has capabilities to read project files and execute local shell commands for linting and testing.
- Sanitization: No explicit sanitization or filtering is defined for the code content before it is processed by the agent's reasoning engine.
Audit Metadata