grade-report
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill instructions or metadata. The skill's behavior is consistent with its stated purpose of analyzing research corpus quality.
- [DATA_EXFILTRATION]: The skill accesses local files in .aiwg/research/quality-assessments/ and source file frontmatter. These are local read operations necessary for generating the report. No evidence of data being sent to external servers or unauthorized locations was found.
- [PROMPT_INJECTION]: The skill processes data from research sources which constitutes an indirect prompt injection surface. 1. Ingestion points: .aiwg/research/quality-assessments/ and source frontmatter quality fields. 2. Boundary markers: Absent. 3. Capability inventory: File write access to .aiwg/reports/grade-report.md. 4. Sanitization: Absent. The risk is minimal as it only generates local summaries without executing untrusted code.
Audit Metadata