skills/jmagly/aiwg/grade-report/Gen Agent Trust Hub

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
Risk Level
SAFE
Analyzed
Jun 18, 2026, 12:25 PM
Security Audit — agent-trust-hub — grade-report