self-improving-agent

Warn

Audited by Runlayer on Mar 15, 2026

Risk Level: MEDIUM
Scan Summary
Max Score
81%
Files
10
Flagged
2
Chunks
12
Flagged Files (2)
self-improving-agent/SKILL.mdMEDIUM
81.3%

Privilege Escalation

Shadow Persistence

Context Poisoning

self-improving-agent/hooks/session-end.shLOW
63.7%

Tool passed security scan

Passed Files (8)Click to expand
self-improving-agent/README.mdOK
40.5%

Tool passed security scan

self-improving-agent/hooks/post-bash.shOK
31.7%

Tool passed security scan

self-improving-agent/references/appendix.mdOK
23.2%

Tool passed security scan

self-improving-agent/memory/semantic-patterns.jsonOK
22.7%

Tool passed security scan

self-improving-agent/hooks/pre-tool.shOK
20.8%

Tool passed security scan

self-improving-agent/templates/validation-template.mdOK
4.7%

Tool passed security scan

self-improving-agent/templates/correction-template.mdOK
3.0%

Tool passed security scan

self-improving-agent/templates/pattern-template.mdOK
2.2%

Tool passed security scan

Audit Metadata
Max File Score
81%
Classification
KNOWN_SERVER_ALL_UNKNOWN
Files Scanned
10
Files Flagged
2
Chunks Analyzed
12
Analyzed
Mar 15, 2026, 03:06 AM
Security Audit — runlayer — self-improving-agent