Caveat verdict

anamnesis-hub

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

Describes a local four-tier memory architecture using Ollama, SQLite, and local markdown files with scheduled sync pipelines; all operations are local or to user-controlled cloud services with no evidence of exfiltration or manipulation.

⚠ 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.

0
security
100
transparency
90
maintenance

Permission integrity

Accesses agent memory/configuration files

agent_memory

Findings (12)

Pattern match critical

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

references/setup-guide.md · code · curl -fsSL https://ollama.com/install.sh | sh

Pattern match critical

Pipe to sh — executes piped content as shell commands

references/setup-guide.md · code · | sh

Pattern match critical

Recursive delete from root or home — destructive command

references/upgrade-reset.md · code · rm -rf ~

Pattern match high

HTTP request to bare IP address — common in malicious payloads

references/setup-guide.md · code · http://127.0.0.1

Pattern match high

Accesses OpenClaw config/secrets directly

references/setup-guide.md · code · ~/.openclaw/openclaw.json

Pattern match high

Possible hardcoded credential

scripts/auto_memory_extract.py · prose · downgraded · API_KEY="): key = line.split(

Pattern match high

Pipe to python — executes piped content as Python code

scripts/daily-memory-pipeline.sh · prose · downgraded · | python3

Pattern match medium

References agent memory files

SKILL.md · frontmatter · MEMORY.md

Pattern match medium

subprocess execution — runs system commands from Python

scripts/auto_memory_extract.py · prose · downgraded · subprocess.run(

Pattern match medium

References sudo — requests elevated privileges

scripts/auto-setup.sh · prose · downgraded · sudo

Pattern match low

Python urllib.request — network access

scripts/auto_memory_extract.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

scripts/auto_memory_extract.py · prose · downgraded · os.environ.get(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/B/C/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.

agent_memory

Is this flag fair?

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