The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill enables the agent to ingest and process data from the bd (beads) tracking system, which constitutes an external data source.
Ingestion points: The agent retrieves content using commands such as bd show, bd ready, bd search, and bd comments show, which read data from the local .beads/ directory and synchronized remote sources.
Boundary markers: The instructions do not define delimiters or provide specific warnings for the agent to ignore potentially malicious instructions embedded in issue titles or descriptions.
Capability inventory: The agent has access to execute shell commands, including git synchronization (git push, git commit) and development tools (pnpm, npm, cargo).
Sanitization: There is no evidence of data sanitization or integrity checking for the content retrieved from the issue tracker.
[COMMAND_EXECUTION]: The skill guides the agent to perform various shell-based operations to manage work items and the development environment.
Evidence: The workflow involves commands like bd sync, bd doctor, and bd hooks install, the latter of which configures the local git environment.

bd