Caveat verdict

python-sdk

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Accesses credentials AND encodes data

Skill provides a Python SDK for the inference.sh AI platform using a user-installed package; all API calls target the declared inference.sh service and serve the stated AI application development purpose.

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
40
transparency
70
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 high

Accesses credentials AND encodes data — may obfuscate stolen credentials

LLM02 · ASI03 · ASI04

Permission integrity

Performs file operations but does not declare file-accessing binaries

file_read

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="inf_your_key

Pattern match critical

Uses eval() — can execute arbitrary code

references/tool-builder.md · code · eval(

Pattern match high

Data URI with base64 payload — may embed malicious content

references/files.md · code · data:application/pdf;base64,

Pattern match medium

Python aiohttp session — async network access

references/files.md · code · aiohttp.ClientSession

Permissions & capabilities

No declared permissions — minimal attack surface.

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