Caveat verdict

alva

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

Accesses agent memory/notes AND makes external network calls

Agentic finance platform for data queries, backtesting, and analytics via the alva CLI; agent_memory and network_out are appropriate for a cloud-side analytics platform that runs persistent financial playbooks.

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.

0
security
50
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 critical

Accesses agent memory/notes AND makes external network calls — may leak personal data

LLM02 · LLM07 · ASI03 · ASI06

Capability combination high

Accesses agent memory AND makes external network calls — may leak conversation history

LLM02 · LLM07 · ASI06

Permission integrity

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

network_out

Accesses agent memory/configuration files

agent_memory

Findings (6)

Pattern match critical

<script> tag in markdown — potential code injection

references/design-components.md · code · <script

Pattern match medium

References agent memory files

SKILL.md · code · MEMORY.md

Pattern match medium

Instructs covert action — may act without user awareness

references/api/push-subscriptions.md · prose · downgraded · silently

Pattern match medium

Uses exec() — may execute shell commands

templates/thesis/example/feeds/ai-bottleneck-narrative.js · prose · downgraded · exec(

Pattern match low

Popular HTTP library — network access

SKILL.md · prose · downgraded · got

Pattern match low

Makes HTTP request to external URL

SKILL.md · code · fetch("https://

Permissions & capabilities

No declared permissions — minimal attack surface.

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