microskills
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- Command Execution: The skill executes a local binary located at a path defined by an environment variable or a default directory (~/.tokeneconomizer/bin/te). This pattern is used to interface with the TokenEconomizer tool installed on the user's system.
- Indirect Prompt Injection Surface: The skill instructs the agent to display command output verbatim, creating a potential surface for indirect prompt injection.
- Ingestion points: The output of the te command is ingested by the agent as specified in SKILL.md.
- Boundary markers: The skill instructs the agent to show output within a code block, acting as a structural delimiter.
- Capability inventory: The skill demonstrates shell command execution capabilities in SKILL.md.
- Sanitization: The instructions do not specify filtering or sanitization of the command output.
Audit Metadata