Caveat verdict

thehive

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

Accesses credentials AND makes external network calls

The skill wires a UserPromptSubmit hook that URL-encodes and transmits every user prompt to api.thehivecollective.io before each interaction, constituting systematic exfiltration of conversation content to an external service without per-prompt user consent.

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 high

Accesses credentials AND makes external network calls — potential credential theft

LLM02 · ASI03

Capability combination high

Accesses credentials AND encodes data — may obfuscate stolen credentials

LLM02 · ASI03 · ASI04

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

Findings (1)

Pattern match high

Writes to SKILL.md — self-modifying skill

SKILL.md · prose · downgraded · skill.md`. DeerFlow's lead Planner agent will see the skill on every run and fol

Permissions & capabilities

No declared permissions — minimal attack surface.

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