openclaw-agent-scaffolder

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill references local application paths including ~/clawd/shared/TEAM-DIRECTORY.md and ~/clawd/shared/PORT-REGISTRY.md. These files are accessed to prevent naming and port conflicts during the scaffolding process, which is consistent with the skill's purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input during the requirements interview and interpolates it into generated workspace files like SOUL.md. This establishes a surface for indirect prompt injection, though it is inherent to the skill's primary function. 1. Ingestion points: User interview responses via AskUserQuestion. 2. Boundary markers: None explicitly defined in the output templates. 3. Capability inventory: Bash, Read, and Write tools are available to the resulting agents. 4. Sanitization: No explicit validation or sanitization of user input is implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 02:29 PM
Security Audit — agent-trust-hub — openclaw-agent-scaffolder