skills/open-gsd/gsd-core/gsd-capture/Gen Agent Trust Hub

gsd-capture

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs routine task management operations. All file access is restricted to local project directories (.planning/, ROADMAP.md) and configuration paths (~/.claude/gsd-core/) consistent with its stated purpose.
  • [SAFE]: Analysis of the routing logic confirms it only parses flags and delegates to local workflow files. No external network requests or suspicious file access patterns were detected.
  • [SAFE]: While the skill ingests untrusted user input via $ARGUMENTS and passes it to subsequent workflows, this is standard behavior for a task capture tool and no malicious patterns were identified in the execution context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 09:38 PM
Security Audit — agent-trust-hub — gsd-capture