reflect-skills-from-memory
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell pipelines (e.g.,
pwd | sed 's/\//-/g') to determine the location of project-specific memory files in the user's home directory. - [COMMAND_EXECUTION]: It triggers a local Python script (
plugin-optimizer/scripts/validate-plugin.py) to validate changes made to skills. - [SAFE]: The skill's access to the
~/.claude/projects/directory is consistent with its stated purpose of managing agent-specific project memory. - [SAFE]: Strong procedural safeguards are included, such as mandatory verification of memory-based claims against the actual source code before any modifications are applied.
Audit Metadata