kernel-ops-docs-publish

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists entirely of instructional text for a documentation publishing workflow. No executable scripts, binaries, or configuration files are present in the skill package.
  • [NO_CODE]: There are no code implementations, subprocess calls, or tool definitions that could perform operations on the host system or network.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests external data including video scripts, production plans, and metadata.
  • Ingestion points: Step 3 (video script/production plan) and Step 5 (publishing package assembly) involve processing external content.
  • Boundary markers: None identified in the instructions.
  • Capability inventory: The skill lacks technical capabilities (file system access, network operations, or code execution) to act upon malicious instructions.
  • Sanitization: Not mentioned, but not applicable given the lack of executable capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 09:02 AM
Security Audit — agent-trust-hub — kernel-ops-docs-publish