coding-principles-and-best-practices
Pass
Audited by Gen Agent Trust Hub on Nov 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses standard Git commands to facilitate the code review process by identifying local changes.
- Evidence: The skill instructs the agent to run
git diff --cached,git status --short, andgit diff <base>...HEAD(found inSKILL.md) to collect the code changes that require review. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted code provided by the user or found in the repository, which could potentially contain malicious instructions aimed at influencing the agent's review behavior.
- Ingestion points: Untrusted data enters the agent context through the output of
git diffand file content reads as specified in the 'Selecting changes for a Git review' section ofSKILL.md. - Boundary markers: Absent; there are no specific instructions or delimiters provided to the agent to distinguish between the review instructions and potential instructions embedded within the code being analyzed.
- Capability inventory: The skill executes shell commands (Git) and generates detailed natural language reports based on the analyzed code (
SKILL.md). - Sanitization: Absent; the skill does not specify any sanitization, escaping, or filtering of the code content before it is processed by the agent.
Audit Metadata