cursor-weekly-review
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs standard repository analysis by reading git commit history and configuration to generate an executive summary. No malicious patterns, unauthorized data exfiltration, or dangerous execution capabilities were identified.
- [EXTERNAL_DOWNLOADS]: The skill metadata references the official Cursor plugins repository on GitHub for its source code and license information, which is a recognized and trusted service.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from git commit messages and diffs. While this represents an injection surface, the risk is negligible as the skill only produces text output and does not utilize exploitable capabilities such as shell execution or network access.
- Ingestion points: Git commit history and repository diffs (SKILL.md).
- Boundary markers: Absent.
- Capability inventory: None identified; the skill logic is restricted to text generation.
- Sanitization: Absent.
Audit Metadata