review
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill analyzes untrusted source code provided by the user or fetched from the repository, creating a potential vector for indirect prompt injection.
- Ingestion points: The skill ingests data from the user-provided
$ARGUMENTSand the output of thegit diffcommand. - Boundary markers: There are no explicit delimiters or protective instructions used to isolate the instructions from the code content being reviewed.
- Capability inventory: The skill utilizes powerful tools including
Read,Grep,Glob, andBash, which could be abused if the agent is misled by malicious comments or code logic. - Sanitization: No validation or sanitization of the input code is performed before analysis.
Audit Metadata