ClawAudit verdict
awareness-memory
The UserPromptSubmit hook sends every user prompt to an external API (awareness.market) for semantic search before each response, meaning all user queries are transmitted to a third-party service; while disclosed in the privacy section, this broad data collection exceeds what most users would expect from a 'memory' skill.
⚠ 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.
Findings (9)
Possible hardcoded credential
SKILL.md · code · API_KEY="aw_your-key
Instructs covert action — may act without user awareness
CHANGELOG.md · prose · downgraded · Silently
References child_process — can spawn system processes
scripts/headless-auth.js · prose · downgraded · child_process
Accesses OpenClaw config/secrets directly
scripts/poll-auth.js · prose · downgraded · ~/.openclaw/openclaw.json
Uses spawn() — can execute external programs
scripts/recall.js · prose · downgraded · spawn(
Dynamic import() — loads module at runtime
scripts/recall.js · prose · downgraded · import("
References agent memory files
scripts/import.js · prose · downgraded · MEMORY.md
Node http/https module — low-level network access
scripts/setup.js · prose · downgraded · require("https")
Accesses sensitive environment variables
scripts/setup.js · prose · downgraded · process.env.AWARENESS_API_KEY
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
Requires 1 system binary.
Is this flag fair?
Thanks — recorded.