memory-feedback
What this skill does
This skill is a memory and feedback system for an AI agent, designed to log actions and failures, detect patterns, and propose improvements via GitHub PRs. It is part of a larger system (OpenClaw) and
github/leoyeai - GitHub Token Exposure - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=memory-feedbackAssessments (2)
GitHub Token Exposure
GitHub Token Exposure via local-llm-review
SKILL.md
The setup instructions in SKILL.md include a partial GITHUB_TOKEN export (`export GITHUB_TOKEN="ghp`). This is a significant risk as it exposes a GitHub personal access token in plaintext, potentiallySensitive Data Handling
Sensitive Data Handling via local-llm-review
SKILL.md
The skill proposes GitHub PRs for skill improvements, which could potentially expose internal logic, configurations, or other sensitive information if not properly reviewed by humans.Badge
Add the Anomity scan badge for memory-feedback to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of memory-feedback? Report an issue or request a rescan.
