Caveat verdict

transmissionbot

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

Accesses credentials AND encodes data

This skill implements end-to-end encrypted agent-to-agent messaging via the documented TransmissionBot API; it generates cryptographic key pairs locally, credential_access is limited to managing the agent's own identity state file, and all behavior matches the stated secure messaging 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.

30
security
40
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 encodes data — may obfuscate stolen credentials

LLM02 · ASI03 · ASI04

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

Findings (2)

Pattern match medium

Sets world-executable permissions

references/REFERENCE.md · code · chmod 700

Pattern match medium

Accesses system credential store

references/REFERENCE.md · prose · downgraded · keychain

Permissions & capabilities

Requires 1 system binary. (1 elevated: npm).

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