Caveat verdict

hippocampus-memory

hippocampus

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

The skill seems to provide a memory system for AI agents, with no indication of malicious behavior or security threats.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

45
security
80
transparency
70
maintenance

Findings (5)

Pattern match high

Instructs covert action — may act without user awareness

CONFIG-UPGRADE.md · code · silently

Pattern match high

<script> tag in markdown — potential code injection

scripts/generate-dashboard.sh · prose · downgraded · <script>

Pattern match medium

Uses spawn() — can execute external programs

scripts/encode-pipeline.sh · prose · downgraded · spawn (

Pattern match low

References agent memory files

prompts/recall-patterns.md · prose · downgraded · MEMORY.md

Pattern match low

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?

Check another skill Browse the registry Auditing your own skills or configs? Use the API