test-consult
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious behavior, data exfiltration, or unauthorized network access was detected. The skill's operations are restricted to read-only analysis of the local file system.
- [NO_CODE]: The skill consists entirely of instructional markdown and does not include any executable scripts or binary files.
- [PROMPT_INJECTION]: Minor risk of indirect prompt injection exists because the skill reads external data like test reports and failure logs. However, this data is only used to inform recommendations through agent delegation, posing no direct security risk. Ingestion points: test directories, coverage reports, and failure logs (SKILL.md); Boundary markers: none identified; Capability inventory: Glob, Grep, Read, and Task tools; Sanitization: none specified.
Audit Metadata