ClawAudit verdict
gradient-inference
Accesses credentials AND makes external network calls
Unofficial community skill that uses GRADIENT_API_KEY solely to call DigitalOcean's documented Gradient Serverless Inference API endpoints; all network usage is consistent with its stated LLM inference purpose.
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.
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.
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Permission integrity
network_out
Findings (4)
Possible hardcoded credential
SKILL.md · code · API_KEY="your-model-access-key
Pipe to python — executes piped content as Python code
SKILL.md · code · | python3
Python os.environ.get — reads environment variable
scripts/gradient_chat.py · prose · downgraded · os.environ.get(
Base64 encoding/decoding
scripts/gradient_image.py · prose · downgraded · base64-encode
Permissions & capabilities
Requires 1 environment variable. (1 sensitive: GRADIENT_API_KEY). Requires 1 system binary.
network_outcredential_accessnetwork_in Thanks — recorded.