start-quest
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes contents of markdown files within the repository (
quest/directory) as instructions for the agent. This creates a surface for indirect prompt injection if those files contain malicious instructions.\n - Ingestion points:
quest/AGENTS.md,quest/*.md.\n - Capability inventory: Shell command execution via
ripgrepandgit.\n - Boundary markers: Absent.\n
- Sanitization: Absent.\n- [COMMAND_EXECUTION]: The skill uses
ripgrepandgittools. It interpolates a user-provided questline directory into a shell command (<base>), which could lead to command injection if the agent does not strictly validate the input as a safe directory path.
Audit Metadata