skills/delorenj/bhappy/gsd-add-phase/Gen Agent Trust Hub

gsd-add-phase

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill references absolute file paths for its execution context and workflow logic located within the author's home directory (/home/delorenj/). This is consistent with a local-first automation tool.
  • [PROMPT_INJECTION]: The skill exposes a potential surface for indirect prompt injection by processing user-provided phase descriptions. * Ingestion points: User input captured via the {{GSD_ARGS}} parameter. * Boundary markers: None present in the skill manifest. * Capability inventory: The skill facilitates agent spawning (spawn_agent) and file system modifications including directory creation and text file updates. * Sanitization: Input sanitization is not explicitly defined in the entry-point manifest.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 04:26 AM
Security Audit — agent-trust-hub — gsd-add-phase