mx-review
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from a file path provided in
$ARGUMENTS. If the target file contains malicious instructions formatted as comments or strings, the agent might inadvertently follow them during the review process. - Ingestion points: Reads code from the file path provided in
$ARGUMENTS. - Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" warnings to isolate the code content from the agent's task instructions.
- Capability inventory: The skill documentation does not list specific dangerous tools, but the underlying agent environment typically possesses file system and potentially network access.
- Sanitization: There is no evidence of sanitization or filtering of the ingested file content.
Audit Metadata