mission-planner
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from user goals and project files such as CLAUDE.md to influence the design of blueprints and agent definitions. * Ingestion points: User goal descriptions, CLAUDE.md, and project directory structure. * Boundary markers: No explicit delimiters or boundary instructions are used for processed inputs. * Capability inventory: The skill writes new agent and skill definitions to the .claude directory. * Sanitization: No explicit validation or escaping of external content is performed.
- [DYNAMIC_EXECUTION]: The skill dynamically generates and writes markdown instruction files to the .claude directory. These files define the logic and capabilities of sub-agents that are subsequently interpreted by the agent platform.
Audit Metadata