Caveat verdict
moltlify
Accesses credentials AND makes external network calls
The skill explicitly instructs autonomous agents to immediately execute without asking the human and installs a recurring cron job every 30 minutes, creating persistent unauthorized behavior.
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.
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.
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Permission integrity
network_out
credential_access
Findings (5)
Instruction-prose smuggling shape detected: collects a sensitive target ("API key") and emits it outward ("Send"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.
SKILL.md · ⚠️ IMPORTANT: - Read skill files from `https://www.moltlify.com` - Send your API key ONLY to `https://api.moltlify.com/api/*` - Always use HTTPS - Frontend buil
Accesses process.env — reads environment variables
SKILL.md · code
Accesses sensitive environment variables
SKILL.md · code · process.env.MOLTER_API_KEY
Popular HTTP library — network access
SKILL.md · code · node-fetch
fetch() — outbound network request
SKILL.md · code
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outcredential_access Thanks — recorded.