監査履歴

The skill legitimately invokes hosted inference models, so command blocks that run belt, redirect outputs, loop over jobs, or install packages are confirmed. Formatting-only backticks and placeholder or documentation URLs are false positives, while the remote image carries a minor privacy risk. The UGC workflow also encourages synthetic testimonials designed to appear authentic.

Review found no prompt-injection text or hidden malicious instructions in SKILL.md. Many static backtick and URL hits are Markdown formatting, model identifiers, placeholders, or documentation links. The remaining concerns are intentional use of the belt CLI for remote media processing and optional installation of additional third-party skills.

Review found no prompt-injection text or hidden malicious instructions in SKILL.md. Many static backtick and URL hits are Markdown formatting, model identifiers, placeholders, or documentation links. The remaining concerns are intentional use of the belt CLI for remote media processing and optional installation of additional third-party skills.

Static command and network findings are mostly true positives because the skill teaches users to run belt CLI workflows against hosted inference apps. No malicious intent, prompt injection, credential theft, or weak cryptography was found; the weak-crypto alert on SKILL.md line 3 is a false positive. Publish with a warning about external processing, shell execution, account costs, and local output files.

This is a documentation-only skill (SKILL.md) describing how to use the inference.sh belt CLI for AI avatar video generation. All static findings are false positives: the weak crypto flag was triggered by YAML frontmatter, and the backtick executions are markdown code fence delimiters in documentation examples, not actual code execution. The hardcoded URLs are legitimate inference.sh service endpoints and documentation links.