The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local bash scripts for structural validation. It calls its internal validate-order-md.sh and a vendor-related script validate-takt-files.sh from the takt-piece skill.
[PROMPT_INJECTION]: The skill exhibits vulnerability to indirect prompt injection (Category 8). 1. Ingestion points: It reads task metadata from .takt/tasks.yaml and processes user-provided requirements in SKILL.md. 2. Boundary markers: No delimiters or explicit instructions are provided to the agent to ignore embedded commands in the data. 3. Capability inventory: The skill has the capability to execute shell commands via bash as defined in the validation steps. 4. Sanitization: There is no evidence of sanitization or escaping of external content before it is interpolated into task files.

takt-task