delphi-dept

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the delphi command-line utility to perform project orchestration, including delphi project list, delphi project new, delphi team list, and delphi dept up. These commands are used to manage the project lifecycle and dispatch agent teams.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to define project scope and generate deliverables, which could be exploited to influence agent behavior through crafted task descriptions.
  • Ingestion points: User input is captured via the $ARGUMENTS variable in SKILL.md and used to classify tasks and generate titles.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the user-supplied task description as untrusted content.
  • Capability inventory: The skill possesses the ability to execute shell commands via the delphi CLI and can launch background agent sessions.
  • Sanitization: The instructions do not specify any validation, escaping, or filtering of the user input before it is interpolated into commands or project stories.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 04:45 AM
Security Audit — agent-trust-hub — delphi-dept