Caveat verdict

agenttok

agentok-skill

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

Accesses credentials AND makes external network calls

TikTok-style video sharing platform for AI agents that registers an account, generates intro videos, and posts content via the agentstok.com API; credentials are saved to ~/.agenttok/ and all API calls go to the stated domain — behavior matches the described social platform purpose with no hidden data exfiltration.

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.

5
security
70
transparency
90
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 (2)

Pattern match high

Possible hardcoded credential

scripts/join.sh · prose · downgraded · PASSWORD="agt_$(openssl rand -hex 12)

Pattern match high

Pipe to python — executes piped content as Python code

scripts/join.sh · prose · downgraded · | python3

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