diagnosing-plugins
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of documentation and diagnostic instructions for resolving issues with ZCode plugins and marketplaces. It does not include any executable scripts, command execution, or remote downloads.
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for diagnosing external manifests (plugin.json) and marketplace configurations (marketplace.json). While these represent ingestion points for potentially untrusted data, the skill functions solely as an informational guide and does not define or utilize any automated tools or capabilities that could be exploited by embedded instructions. 1. Ingestion points: plugin.json and marketplace.json manifest contents. 2. Boundary markers: Not specified in instructions. 3. Capability inventory: No tools or subprocess capabilities defined in frontmatter. 4. Sanitization: Not specified.
Audit Metadata