frontend-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data by reading frontend source code files (.tsx, .ts, .js) and git diffs provided by the user. While this creates a potential surface for indirect prompt injection (where malicious instructions could be hidden in code comments), the skill does not possess high-privilege capabilities or access to dangerous tools that could be exploited.
- Ingestion points: Reads content from local component files and git working-tree changes.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the review process.
- Capability inventory: The skill is limited to performing text analysis and generating structured feedback within the chat context.
- Sanitization: No specific sanitization or filtering of the ingested code content is performed before analysis.
- [SAFE]: The skill references an external link to a GitHub issue (langgenius/dify). GitHub is a well-known service, and the reference is used for documentation purposes regarding a specific bug pattern.
Audit Metadata