The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructions direct the user to clone a repository from https://github.com/webzler/agentMemory.git to initialize functionality. This introduces code from a third-party source into the agent's environment.- [REMOTE_CODE_EXECUTION]: The setup process involves running npm install and npm run compile on the cloned repository. This leads to the execution of code and scripts defined by the external repository during the build and installation phases.- [COMMAND_EXECUTION]: The skill relies on several shell commands for its setup and operation, including git clone, npm install, and npm run start-server. These commands execute logic provided by the external project files.- [INDIRECT_PROMPT_INJECTION]: The skill acts as a memory management system that reads and searches content via memory_read and memory_search. If the stored memory content includes adversarial instructions, the agent could potentially process and follow them.
Ingestion points: External data is ingested through the memory_read and memory_search tools defined in SKILL.md.
Boundary markers: None identified in the skill instructions to delimit stored content from system instructions.
Capability inventory: The skill has the capability to execute shell commands as described in the Setup and Dashboard sections of SKILL.md.
Sanitization: There is no evidence of sanitization or filtering for the content retrieved from the memory bank.

agent-memory-mcp