skills/borghei/claude-skills/wwas/Gen Agent Trust Hub

wwas

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill includes Python scripts (backlog_alignment_checker.py, invest_gate_checker.py, and wwas_quality_scorer.py) that parse external JSON backlog data. This creates a surface for indirect prompt injection where malicious instructions within data fields could be reflected in the tools' output reports.
  • Ingestion points: Data is ingested via the --backlog and --items CLI arguments in the scripts.
  • Boundary markers: No delimiters are used to separate the ingested data from the report output.
  • Capability inventory: Scripts are limited to read-only operations on input files and standard output.
  • Sanitization: No sanitization or escaping of the input data is performed before inclusion in reports.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 01:08 AM