eisenhower
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a set of behavioral instructions for an AI agent to categorize task lists provided by the user. It does not require any tool permissions, perform network activity, or attempt to modify the local file system.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user input via the $ARGUMENTS placeholder in SKILL.md and the command implementation files. However, the attack surface is restricted because the skill lacks access to any sensitive tools, data, or system commands, rendering potential injection attempts ineffective.
- Ingestion points: User-provided task lists passed through the $ARGUMENTS placeholder in SKILL.md, commands/eisenhower.md, and commands/prioritize.md.
- Boundary markers: None present.
- Capability inventory: No subprocess calls, network operations, or file-write permissions are requested or used.
- Sanitization: None present.
Audit Metadata