beads
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides shell commands for project task management using the 'bd' CLI, including commands to list, show, update, and create tasks as seen in SKILL.md.- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests external task data which could contain untrusted content.\n
- Ingestion points: Task data is read via 'bd show' and 'bd list' commands in SKILL.md.\n
- Boundary markers: No explicit delimiters or instructions are provided to isolate task content from agent instructions.\n
- Capability inventory: The skill utilizes shell execution for task management operations in SKILL.md.\n
- Sanitization: No specific sanitization or validation of task content is described before the data is processed by the agent.
Audit Metadata