The Agent Skills Directory

[SAFE]: The skill serves as a diagnostic and maintenance tool for semantic memory systems. Its operations are focused on reading local configuration (manifest.json), validating filesystem structure, and performing content integrity checks. No unauthorized network operations, credential access, or obfuscation techniques were detected.
[COMMAND_EXECUTION]: The skill documentation describes the use of the aiwg memory command-line interface for storage operations (read, list, get, put, append-log). These are standard operational commands within the platform's architecture for managing memory artifacts.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes consumer-provided content.
Ingestion points: Memory pages (Markdown files), the .log.jsonl file, and the consumer's manifest.json (specifically the lintRules field).
Boundary markers: No explicit boundary markers or delimiters for untrusted data are specified in the processing logic.
Capability inventory: The skill has the capability to write to the filesystem (index.md, log files) and delegate execution to other skills defined in the manifest.
Sanitization: No explicit sanitization or validation of the content within the memory pages is described, which is typical for a linting tool that evaluates the integrity of the data itself.

memory-lint