The Agent Skills Directory

[NO_CODE]: The skill consists entirely of markdown instructions (SKILL.md) and does not include any associated scripts, binaries, or configuration files.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from external files, creating a vulnerability surface where malicious instructions embedded in that data could influence the agent.
Ingestion points: The skill explicitly identifies TASK_ID.task.json, feature documentation, and epic documentation as authoritative inputs for the execution process.
Boundary markers: The instructions do not define specific delimiters or directives to ignore potentially malicious embedded instructions within the task-related input files.
Capability inventory: The skill grants the agent authority to modify project files and execute shell commands for linting, typechecking, and running unit/integration tests.
Sanitization: There is no evidence of validation, sanitization, or filtering mechanisms for the content read from the task files before it is processed by the agent.

mb-execute