-
fix: v2.36.1 security hardening (Gen Agent Trust Hub FAIL + Snyk WARN)
frostbyte_neo 发布于
2026-05-01 17:18:12 +00:00 Closes security audit findings from skills.sh platform audits.
Stop hook: replace broad Get-ChildItem -Recurse over ~/.claude/plugins/cache
with resolution through $CLAUDE_SKILL_DIR env var first, then two specific
known install paths. Removes arbitrary code execution risk from cache
directory poisoning.PowerShell ExecutionPolicy: Bypass -> RemoteSigned across all 14 SKILL.md
variants. RemoteSigned allows local scripts while blocking unsigned downloaded
scripts. Bypass was flagged as privilege escalation by Gen Agent Trust Hub.Prompt injection delimiters: UserPromptSubmit and PreToolUse hooks now wrap
injected plan content in ---BEGIN PLAN DATA--- / ---END PLAN DATA--- markers
with explicit model instruction to treat contents as structured data and ignore
embedded instructions. Addresses the lack of sanitization boundary flagged in
the PROMPT_INJECTION finding.Security Boundary docs: updated to document delimiter contract and add
explicit instruction that findings.md content (third-party web/search results)
must be treated as raw data. Addresses Snyk W011 third-party content exposure.下载附件