mikado-method
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves a surface where user-supplied information is interpolated into suggested shell commands, which could be exploited if malicious input is provided.\n
- Ingestion points: User input for goals and file paths is processed in the Output Format section of
SKILL.md.\n - Boundary markers: Absent; no instructions to delimit or ignore instructions within user input are provided to the agent.\n
- Capability inventory: The skill encourages shell command generation and usage (specifically git operations) across all provided files.\n
- Sanitization: Absent; no validation or escaping of user input before its inclusion in command templates is mentioned.
Audit Metadata