phoenix-verification-matrix

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a formal process for verification planning within a security spec pipeline. It operates solely on requirement definitions to produce a Markdown-based test matrix. No malicious patterns, data exfiltration, or unauthorized command execution risks were identified.
  • [INDIRECT_PROMPT_INJECTION]: The skill represents a low-risk ingestion surface as it processes requirement statements from external sources (Roles 04, 06, and 07). However, the skill lacks high-privilege capabilities such as file system writes, network requests, or code execution, rendering the surface non-exploitable.
  • Ingestion points: External requirement statements from Roles 04, 06, and 07 are ingested to be mapped to proof methods.
  • Boundary markers: Not explicitly defined in the instruction set.
  • Capability inventory: None detected. The skill only generates a Markdown output table.
  • Sanitization: Not explicitly defined, though the skill itself mandates the creation of tests for prompt injection sanitization in the projects it analyzes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 10:33 AM
Security Audit — agent-trust-hub — phoenix-verification-matrix