The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands grep and git blame to extract data from the local repository. This is an intended capability for the skill's primary purpose.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection attacks.
Ingestion points: The agent reads and processes the content of comments from any file in the repository via the grep command.
Boundary markers: The instructions do not define any delimiters or warning markers to prevent the agent from interpreting the extracted comment text as new instructions.
Capability inventory: The skill has access to shell command execution and local file system write access (to save the ledger).
Sanitization: There is no evidence of sanitization, validation, or filtering of the comment content before it is processed by the agent.

ponytail-debt