skills/zseven-w/dsh-crew/dsh-config/Gen Agent Trust Hub

dsh-config

Pass

Audited by Gen Agent Trust Hub on Oct 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts and parses user arguments to configure session-level parameters such as tier, effort, and timeout.
  • Ingestion points: User-supplied arguments following the command in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing logic.
  • Capability inventory: The skill utilizes the dsh_worker_config tool to read and modify session configuration state.
  • Sanitization: The skill relies on specific key-value mapping (e.g., tier to default_tier) which acts as a basic form of input validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 31, 2026, 01:30 PM