The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses standard shell utilities to traverse directories and search files. Specifically, it uses grep for pattern matching in logs and ls for listing task handoffs in .memories/ and ~/.agents/memories/.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests data from external log files which could be manipulated to include malicious instructions.
Ingestion points: The skill reads data from .memories/ and ~/.agents/memories/ directories.
Boundary markers: There are no explicit delimiters or warnings to the agent to ignore embedded instructions within the retrieved content.
Capability inventory: Includes file system exploration and content searching via ls and grep (SKILL.md).
Sanitization: The skill does not implement any validation or filtering of the content retrieved from the logs before it is processed by the agent.

mem-recall