The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the openspec and bd (Beads) command-line interfaces to automate project management tasks. It dynamically generates shell commands by inserting text extracted from local repository files into command arguments.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted data from local specification files and includes it in the agent's execution context.
Ingestion points: Reads requirements and descriptions from files such as proposal.md, specs/*.md, design/*.md, and tasks.md.
Boundary markers: There are no explicit delimiters or instructions to the agent to treat the imported file content as untrusted data or to ignore instructions contained within those files.
Capability inventory: The skill possesses the ability to execute system binaries (openspec, bd) which can modify the state of the repository and external issue trackers.
Sanitization: No sanitization or escaping is performed on the strings read from files before they are passed as arguments to the bd create command flags.

openspec-beads-import