The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses subprocess calls to execute commands for the bd (classic Beads) and br (beads_rust) trackers, including create, update, sync, and dep cycles checks.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted user-provided documentation to generate issue tracker entries.
Ingestion points: External plans, specs, PRDs, and design documents are ingested as part of the translation process in SKILL.md (Steps 3-5).
Boundary markers: The skill does not define specific boundary markers or delimiters to separate untrusted source text from instructions.
Capability inventory: The skill has the capability to execute shell commands (bd and br CLIs) and modify local tracker state as documented in SKILL.md (Steps 2, 5, 6, and 8).
Sanitization: No sanitization or validation of the input text is performed before it is used to populate issue titles, descriptions, and acceptance criteria.

beads-create