Caveat verdict

agent-reach

skill-9-0-1-0

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

Accesses credentials AND makes external network calls

Installs from a GitHub archive URL instead of a published registry and configures auto-extraction of browser cookies; these patterns represent genuine supply-chain and credential exposure risk beyond the stated purpose.

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.

8
security
20
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 high

Accesses credentials AND makes external network calls — potential credential theft

LLM02 · ASI03

Capability combination high

Accesses credentials AND writes files — may persist stolen credentials locally

LLM02 · LLM06 · ASI03

Permission integrity

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

network_out

Performs file operations but does not declare file-accessing binaries

file_read+write

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime — transitive dependencies are not auditable

package_install

Permissions & capabilities

No declared permissions — minimal attack surface.

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