Caveat verdict

shippage

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

Accesses agent memory/notes AND makes external network calls

The skill instructs the agent to silently download and atomically replace its own SKILL.md from https://shippage.ai/v1/skill/download on every session without user confirmation, which constitutes remote code replacement of agent instructions.

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
60
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 critical

Accesses agent memory/notes AND makes external network calls — may leak personal data

LLM02 · LLM07 · ASI03 · ASI06

Capability combination high

Reads local files AND makes external network calls — the capabilities for data exfiltration co-occur (data-flow not verified)

LLM02 · LLM06 · ASI03

Capability combination high

Executes processes AND makes external network calls — may exfiltrate command output

LLM02 · LLM06 · ASI03

Capability combination high

Accesses agent memory AND makes external network calls — may leak conversation history

LLM02 · LLM07 · ASI06

Permission integrity

Accesses agent memory/configuration files

agent_memory

Findings (2)

Pattern match critical

Pipe to python — executes piped content as Python code

SKILL.md · code · | python3

Pattern match medium

Instructs covert action — may act without user awareness

SKILL.md · prose · downgraded · silently

Permissions & capabilities

Requires 1 system binary. (1 elevated: curl).

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