ClawAudit verdict
hippocampus-memory
The skill uses `install.sh` which may pose a risk if not properly validated.
⚠ 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 (5)
Instructs covert action — may act without user awareness
CONFIG-UPGRADE.md · code · silently
<script> tag in markdown — potential code injection
scripts/generate-dashboard.sh · prose · downgraded · <script>
Uses spawn() — can execute external programs
scripts/encode-pipeline.sh · prose · downgraded · spawn (
References agent memory files
prompts/recall-patterns.md · prose · downgraded · MEMORY.md
Python os.environ.get — reads environment variable
scripts/encode-pipeline.sh · prose · downgraded · os.environ.get(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 2 system binaries.
data_encoding Is this flag fair?
Thanks — recorded.