code-review
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of a markdown configuration file (SKILL.md) and does not include any scripts, binaries, or automated tasks. All instructions are dedicated to performing a senior engineer-level code review.
- [PROMPT_INJECTION]:
- Ingestion points: The skill processes external content (code diffs) via the
$ARGUMENTSplaceholder in theSKILL.mdfile. - Boundary markers: No explicit delimiters or boundary markers are used to separate the reviewer instructions from the untrusted code content being analyzed.
- Capability inventory: The skill has no capabilities to execute commands, access the network, or modify the file system, which significantly limits the potential impact of any indirect prompt injection.
- Sanitization: There is no input sanitization or filtering logic applied to the content provided in
$ARGUMENTS.
Audit Metadata