ClawAudit verdict
shieldcortex
The skill explicitly reads from a broad set of agent configuration directories including ~/.claude/, ~/.cursor/, ~/.windsurf/, ~/.codex/, and .env files, and has optional cloud sync to api.shieldcortex.ai; while justified as a security scanner, scanning credential files across multiple agent installations with optional external network sync is elevated access beyond what most skills require.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
credential_access
Findings (7)
Uses eval() — can execute arbitrary code
SKILL.md · prose · downgraded · eval(
References agent configuration files
SKILL.md · frontmatter · CLAUDE.md
Uses exec() — may execute shell commands
SKILL.md · prose · downgraded · exec(
References child_process — can spawn system processes
SKILL.md · prose · downgraded · child_process
Instructs covert action — may act without user awareness
bundled/cortex-memory-hook/handler.ts · prose · downgraded · silently
Dynamic import() — loads module at runtime
bundled/cortex-memory-hook/handler.ts · prose · downgraded · import("
References agent memory files
bundled/cortex-memory-hook/handler.ts · prose · downgraded · MEMORY.md
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
network_incredential_access Is this flag fair?
Thanks — recorded.