Caveat verdict

sumo-notebook-rag

88
๐ŸŸข Trusted
No high-risk patterns surfaced by the deep scan โ€” automated capability review, not behavioral proof.

Fetches from network AND uses eval/Function

Local RAG search over markdown files using Ollama embeddings and LanceDB; all operations are purely local with no external network calls beyond checking Ollama local server at localhost:11434.

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

25
security
50
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence โ€” it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination critical

Fetches from network AND uses eval/Function โ€” the remote-code-execution pattern (data-flow not verified)

LLM05 ยท LLM06 ยท ASI05

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Findings (1)

Pattern match high

Dynamic import() โ€” loads module at runtime

SKILL.md ยท code ยท import('

Permissions & capabilities

No declared permissions โ€” minimal attack surface.

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