Caveat verdict

duo

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

Accesses credentials AND makes external network calls

The skill explicitly reads multiple local identity files (IDENTITY.md, SOUL.md, USER.md, memory, TOOLS.md) including 'finances, religion/lifestyle preferences, deal-breakers' and sends this compiled sensitive profile data to an external NDAI enclave endpoint, constituting unsolicited exfiltration of personal data beyond the skill's matchmaking 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.

43
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

Permission integrity

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

network_out

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (1)

Pattern match low

References agent memory files

SKILL.md · prose · downgraded · memory.md

Permissions & capabilities

No declared permissions — minimal attack surface.

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