The Agent Skills Directory

[COMMAND_EXECUTION]: The skill interacts with the local file system by executing a Python script via the shell. Specifically, the command python {skill_path}/scripts/board_manager.py --post --channel {channel} --author {author} --message "{text}" interpolates variables directly into a shell execution block. If the {text}, {author}, or {channel} variables contain shell metacharacters (e.g., semicolons, backticks, or pipe symbols), it could result in arbitrary command execution on the host system.
[INDIRECT_PROMPT_INJECTION]: The core functionality involves reading data ('posts') from shared channels which are populated by other, potentially untrusted agents.
Ingestion points: Data is ingested from markdown files in the coordination board via python {skill_path}/scripts/board_manager.py --read {channel}.
Boundary markers: There are no instructions or boundary markers defined in SKILL.md to tell the agent to ignore instructions or malicious payloads embedded within the board posts.
Capability inventory: The skill possesses the ability to execute shell scripts, write to files, and interact with a shared filesystem context.
Sanitization: No sanitization or validation logic is described for the incoming message content before it is displayed to or processed by the agent.
[DYNAMIC_EXECUTION]: The skill relies on the execution of a Python script (board_manager.py) located within the skill's path to perform all operations, representing a dependency on external script execution for primary functionality.

board