Caveat verdict

grafana-foundation-sdk

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

Both reads and writes files

Reference skill for building Grafana dashboards as typed code using the official grafana-foundation-sdk; no credentials, no exfiltration, just code-generation guidance.

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.

33
security
60
transparency
70
maintenance

What it does

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

Capability combination medium

Both reads and writes files — verify scope is limited to intended directories

LLM06 · ASI02

Permission integrity

Performs file operations but does not declare file-accessing binaries

file_read+write

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (3)

Pattern match high

Dynamic import() — loads module at runtime

references/typescript-api.md · code · import ( "

Confirmed in code medium

File write/delete operation

SKILL.md · code

Pattern match medium

Instructs covert action — may act without user awareness

SKILL.md · prose · downgraded · silently

Permissions & capabilities

No declared permissions — minimal attack surface.

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