Local-first memory search and indexing for Openclaw. Use when you need to (1) index memory files, (2) search memory from the CLI, or (3) wire a slash command for memory lookup.
Security Analysis
medium confidenceThe skill's requested actions and resources match its described purpose (local indexing and searching of memory files), but because it instructs the agent to run local scripts that are not included, you should inspect those scripts before executing them.
Name, description, and instructions all describe local indexing/search of memory files (MEMORY.md and memory/**/*.md). There are no unrelated env vars, binaries, or config paths requested.
SKILL.md tells the agent to run scripts/index-memory.py and scripts/search-memory.py and describes which files are indexed and where the cache lives. The instructions do not reference external endpoints or extra credentials. However, the actual scripts are not included in the skill bundle — running arbitrary local scripts can perform any action, so those files must be reviewed before execution.
No install spec is provided (instruction-only). No downloads or archive extraction are requested.
No environment variables, credentials, or special config paths are required; requested access appears proportionate to the stated task.
Skill is not always-enabled and does not request persistent/system-wide privileges. It does not modify other skills or agent configuration.
Guidance
This skill is coherent with its stated purpose (indexing and searching local memory files), but it instructs the agent to execute local Python scripts that were not included for review. Before running or enabling this skill: (1) inspect scripts/index-memory.py and scripts/search-memory.py for network calls, secret access (reads of env vars or other files), subprocess execution, or writes to sensitive locations; (2) run them in a sandbox or with least privilege if possible; (3) ensure the memory/cache/ location is acceptable for your data retention needs; (4) only enable autonomous invocation if you trust the scripts and their behavior. If you cannot review the scripts, treat the skill as untrusted.
Latest Release
v0.1.0
Initial publish
More by @Trumppo
Published by @Trumppo on ClawHub
