Caveat verdict
ssh-tunnel
Fetches from network AND uses eval/Function
Reference documentation for SSH tunneling, port forwarding, and key management; all patterns are standard sysadmin operations with no exfiltration or malicious 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.
Fetches from network AND uses eval/Function — the remote-code-execution pattern (data-flow not verified)
LLM05 · LLM06 · ASI05
Receives external input AND uses eval — the remote code-injection pattern (data-flow not verified)
LLM01 · LLM05 · ASI01 · ASI05
Accesses system credential store AND makes external network calls
LLM02 · ASI03
Permission integrity
network_out
file_read+write
Findings (3)
Accesses .ssh directory
SKILL.md · code · .ssh/
References SSH/GPG private keys
SKILL.md · code · ssh-key
Sets world-executable permissions
SKILL.md · code · chmod 700
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 1 system binary. (1 elevated: ssh).
network_innetwork_outcredential_storefile_writedynamic_eval Thanks — recorded.