deliverable-charter

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill includes explicit instructions (HARD-GATE) that prevent the agent from taking autonomous actions like writing to disk or drafting multiple sections without user confirmation.
  • [COMMAND_EXECUTION]: Local shell commands are used for project slug derivation via git config and report generation using internal scripts. These are standard operations within the intended workflow.
  • [DATA_EXFILTRATION]: Data handling is restricted to the local project directory and standard git configuration, with no unauthorized external transmission observed.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 08:56 AM