Scan Report
5 /100
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement
A pure-documentation self-improvement skill that logs learnings to markdown files with explicit secret-avoidance policies and no code execution. No malicious behavior found.
Safe to install
Approve for use. No action required.
| Resource | Declared | Inferred | Status | Evidence |
|---|---|---|---|---|
| Filesystem | WRITE | WRITE | ✓ Aligned | SKILL.md:creates .learnings/ dir and markdown files in workspace root |
| Shell | WRITE | WRITE | ✓ Aligned | SKILL.md: mkdir -p and file creation commands — scoped to project .learnings/ on… |
| Network | NONE | NONE | — | No network tool usage — external URLs are documentation links only |
| Environment | NONE | NONE | — | SKILL.md explicitly instructs: 'Never log secrets, tokens, private keys, environ… |
| Clipboard | NONE | NONE | — | No clipboard access declared or observed |
| Browser | NONE | NONE | — | No browser tool usage |
| Database | NONE | NONE | — | No database access |
| Skill Invoke | NONE | NONE | — | No skill self-invocation |
1 findings
Medium External URL 外部 URL
https://agentskills.io/specification SKILL.md:581 File Tree
1 files · 19.0 KB · 603 lines Markdown 1f · 603L
└─
SKILL.md
Markdown
Security Positives
✓ Explicitly prohibits logging secrets, tokens, private keys, environment variables, and full source/config files
✓ Single markdown file with no executable code, scripts, or binaries
✓ File writes are scoped to project-local .learnings/ directory only
✓ External URLs are read-only documentation links, not fetches or downloads
✓ No obfuscation, base64, eval, or hidden functionality
✓ No credential harvesting, data exfiltration, or privilege escalation
✓ Hook integration is fully opt-in and requires explicit user configuration
✓ git clone targets a named directory (~/.openclaw/skills/) with no auto-execution