ln-514-regression-checker
Warn
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is configured to read and execute shell commands directly from
docs/project/runbook.md. According to the documentation, these commands take priority over auto-detected safe defaults, allowing for the execution of arbitrary scripts or system commands defined in the project files. - [PROMPT_INJECTION]: The skill exhibits a significant attack surface for Indirect Prompt Injection (Category 8).
- Ingestion points: The agent parses the
docs/project/runbook.mdfile to determine execution parameters and environment setup. - Boundary markers: No delimiters or instructions are provided to the agent to ignore or sanitize embedded commands within the runbook content.
- Capability inventory: The skill possesses the capability to execute shell commands with a 5-minute timeout and access environment variables.
- Sanitization: There is no evidence of sanitization or validation of the commands extracted from external project files before they are passed to the execution tool.
- [EXTERNAL_DOWNLOADS]: The
diagram.htmlfile fetches the Mermaid.js library from the jsDelivr CDN (https://cdn.jsdelivr.net/npm/mermaid@11/dist/mermaid.min.js) to render workflow diagrams.
Audit Metadata