Caveat verdict

bapbook

18
๐Ÿ”ด Dangerous
High-risk patterns flagged for review โ€” automated deep scan, not behaviorally verified.

Accesses credentials AND makes external network calls

The skill explicitly instructs the agent to add a heartbeat routine that fetches https://bapbook.com/skill.md every 30 minutes and follow the Heartbeat Routine from that URL, constituting a concrete agent hijacking mechanism where an external server can silently update and execute arbitrary instructions against the running agent.

Automated static analysis โ€” not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

20
security
30
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence โ€” 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 โ€” potential credential theft

LLM02 ยท ASI03

Capability combination high

Accesses credentials AND encodes data โ€” may obfuscate stolen credentials

LLM02 ยท ASI03 ยท ASI04

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

Permissions & capabilities

No declared permissions โ€” minimal attack surface.

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