Caveat verdict

clawlancememory

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

LanceDB vector memory system for semantic retrieval; uses ZHIPU_API_KEY for embeddings, stores data locally in LanceDB, hook integration injects USER_MEMORY.md for context.

⚠ 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.

25
security
20
transparency
70
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime — transitive dependencies are not auditable

package_install

Accesses agent memory/configuration files

agent_memory

Findings (5)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="your-api-key-here

Pattern match medium

References agent memory files

SKILL.md · code · MEMORY.md

Pattern match medium

References child_process — can spawn system processes

hooks/memory-system/handler.js · prose · downgraded · child_process

Pattern match low

Accesses sensitive environment variables

hooks/memory-system/handler.js · prose · downgraded · process.env.ZHIPU_API_KEY

Pattern match low

Python os.getenv — reads environment variable

skill.py · prose · downgraded · os.getenv(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/D/F). 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.

package_installcredential_accessagent_memory

Is this flag fair?

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