didericis/bot-bottle
1
0
Fork 0
Code Issues 7 Pull Requests 15 Actions Packages Projects Releases Wiki Activity

docs(research): replace unsourced "20% malicious skills" with cited empirical figures

Browse Source 
The "~20% of ClawHub skills malicious" claim had no traceable source and
is contradicted by the empirical literature. Replace with the Jan 2026
large-scale study (98,380-skill snapshot: 157 confirmed malicious, ~71%
credential harvesters, exfiltration overwhelmingly naive) and add the
arXiv citation. The corrected figures still support the supply-chain
threat point and are defensible under scrutiny.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YcU7nerbg8cVj9R4EkpfLJ
This commit is contained in:
didericis
2026-06-24 09:32:19 -04:00
parent 369d332204
commit 80eca740d6
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/research/local-vs-remote-agent-execution.md
+1 -1
View File
@@ -22,7 +22,7 @@ escapes**, and **whether credentials are short-lived and scoped**.
- Outbound: Docker containers have full internet access by default; no egress monitoring on most home networks - Outbound: Docker containers have full internet access by default; no egress monitoring on most home networks
- Lateral movement: compromised container can reach the LAN — NAS, other machines, internal services - Lateral movement: compromised container can reach the LAN — NAS, other machines, internal services
- Notable: CVE-2025-59536 (CVSS 8.7, Feb 2026) — a poisoned `.claude/settings.json` in a repo gives RCE when Claude Code opens it. `--dangerously-skip-permissions` removes the last gate. - Notable: CVE-2025-59536 (CVSS 8.7, Feb 2026) — a poisoned `.claude/settings.json` in a repo gives RCE when Claude Code opens it. `--dangerously-skip-permissions` removes the last gate.
- Supply chain: MCP servers, skills, and npm packages pulled during agent execution. ~20% of ClawHub skills were found malicious in early 2026. - Supply chain: MCP servers, skills, and npm packages pulled during agent execution. A Jan 2026 large-scale empirical study of a 98,380-skill snapshot confirmed 157 malicious skills, ~71% of them credential harvesters. Exfiltration was overwhelmingly naive — plaintext HTTP to hardcoded endpoints; under 10% used any code obfuscation, and concealment was mostly at the documentation level, not the code level. ([Malicious Agent Skills in the Wild](https://arxiv.org/html/2602.06547v1), arXiv:2602.06547)
**What local topology protects:** **What local topology protects:**
- No inbound attack surface — nothing listening on a public port - No inbound attack surface — nothing listening on a public port