The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional documentation and workflow guidelines. No malicious code, obfuscation, or unauthorized data access patterns were detected.
[COMMAND_EXECUTION]: The skill instructs the agent to utilize a command-line tool named bd (beads) for task initialization and management (e.g., bd quickstart, bd --help). These commands are standard for the skill's stated purpose of local task coordination.
[INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow where the agent reads and writes to collaborative files like FOCUS.md and bd issues. This creates a potential surface for indirect prompt injection if external actors or subagents modify these files with malicious instructions.
Ingestion points: bd issues, FOCUS.md (SKILL.md)
Boundary markers: None provided.
Capability inventory: The skill does not include any executable scripts, but it directs the agent to use CLI tools for task management.
Sanitization: None provided.

task-management