agentskill-kaizen-meta-docs
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEDYNAMIC_CONTEXT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_CONTEXT_INJECTION]: The skill uses a shell command (
find) to dynamically generate a list of markdown files located in the${CLAUDE_PLUGIN_ROOT}/docsdirectory. This occurs at skill load time and is used to provide an index of documentation for the agent. This is a functional use of the feature for discovery. - [INDIRECT_PROMPT_INJECTION]: The output of the file listing is directly injected into the agent's context.
- Ingestion points:
SKILL.md(via dynamic shell command output listing filenames). - Boundary markers: None.
- Capability inventory: The agent can read the files listed in the output.
- Sanitization: None.
Audit Metadata