lint
Pass
Audited by Gen Agent Trust Hub on Jun 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the RUN command to execute standard shell utilities like grep, find, and wc for directory auditing and file analysis.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) as it parses and compares text from wiki pages.
- Ingestion points: Markdown files within the llmwiki/wiki/ directory are read during health check steps.
- Boundary markers: The instructions do not define markers to separate untrusted wiki content from the agent's operational logic.
- Capability inventory: The skill can execute shell commands and modify files (fixing links, updating logs) within the local workspace.
- Sanitization: There is no evidence of sanitization or validation of wiki content before it is processed by the agent.
Audit Metadata