The Agent Skills Directory

[COMMAND_EXECUTION]: The skill constructs and executes a bash command node bin/tb-api.mjs create-task ... using parameters derived from user input and local files. While the execution is restricted to the node runtime via the allowed-tools configuration, the interpolation of external data into shell arguments is a standard surface for command injection if inputs are not properly sanitized.
[PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection by processing data from a local file without validation.
Ingestion points: Reads project lists and task history from the .teambition.md file (SKILL.md, Step 1 and 4).
Boundary markers: No delimiters or instructions are provided to the agent to ignore potentially malicious text embedded within the configuration file.
Capability inventory: The skill has access to the Bash, Read, and Edit tools, allowing it to execute scripts, read system files, and modify local content.
Sanitization: There is no evidence of sanitization or schema validation for the data retrieved from the .teambition.md file before it is used to influence the agent's behavior.

tb-create-task