The Agent Skills Directory

COMMAND_EXECUTION (LOW): The skill instructions advise using Grep search on patterns derived from user questions, which could lead to command injection if the underlying agent implementation executes these as shell commands without proper sanitization.
PROMPT_INJECTION (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) as it retrieves content from memory files in the AI_MEMORY/ directory which are populated by previous, potentially untrusted, interactions. 1. Ingestion points: Memory files in AI_MEMORY/L1-L4. 2. Boundary markers: Absent; the skill does not define delimiters for retrieved memory content. 3. Capability inventory: The skill has read access to the local filesystem for memory retrieval. 4. Sanitization: Absent; no validation or escaping of the retrieved memory data is performed before processing.

mem-query