Caveat verdict
linux-ollama
Accesses credentials AND makes external network calls
Ollama fleet routing skill for Linux machines using pip install ollama-herd and systemd services; all inference stays local, OpenAI-compatible endpoint runs on localhost:11435, no credential exfiltration or remote execution concerns.
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
Accesses credentials AND writes files — may persist stolen credentials locally
LLM02 · LLM06 · ASI03
Permission integrity
network_out
file_read+write
credential_access
package_install
Findings (6)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
SKILL.md · code · curl -fsSL https://ollama.ai/install.sh | sh
Pipe to sh — executes piped content as shell commands
SKILL.md · code · | sh
Possible hardcoded credential
SKILL.md · code · api_key="not-needed
Pipe-to-python pattern — remote code execution risk
SKILL.md · code · curl -s http://localhost:11435/fleet/status | python
Pipe to python — executes piped content as Python code
SKILL.md · code · | python3
References sudo — requests elevated privileges
SKILL.md · code · sudo
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B/F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outpackage_installcredential_accessfile_write Thanks — recorded.