planner

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill frequently executes shell commands via the 'bd' CLI tool (e.g., 'bd show', 'bd create', 'bd dep add') to interact with an issue tracking system and manipulate task dependencies.
  • [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection (Category 8) because it ingests untrusted data from the codebase and external issue descriptions to formulate plans.
  • Ingestion points: Data enters the context via '/plan ' and 'bd show --json' commands.
  • Boundary markers: The instructions do not define delimiters or protective wrapping for the untrusted data being read into the agent's context.
  • Capability inventory: The agent can execute shell commands to modify project state (issue creation and dependency mapping).
  • Sanitization: There is no mention of filtering, escaping, or validating the input from the user or the issue tracker before it is used to influence the agent's planning logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 03:37 PM
Security Audit — agent-trust-hub — planner