ClawAudit verdict

gemma-gemma3

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Accesses credentials AND makes external network calls

Routes LLM requests to local Gemma 3 models via Ollama fleet manager on localhost; no external data exfiltration, models pulled on demand with user confirmation, and credential access is limited to PyPI package installation.

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

0
security
70
transparency
90
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but ClawAudit 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

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (4)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · api_key="not-needed

Pattern match critical

Pipe-to-python pattern — remote code execution risk

SKILL.md · code · curl -s http://localhost:11435/api/ps | python

Pattern match critical

Pipe to python — executes piped content as Python code

SKILL.md · code · | python3

Pattern match low

References agent configuration files

SKILL.md · prose · downgraded · CLAUDE.md

Permissions & capabilities

No declared permissions — minimal attack surface.

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