capability-router
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown instructions and metadata. It does not contain any scripts, binaries, or executable code blocks.
- [SAFE]: Analysis of the skill body confirms it is limited to providing reasoning logic and generating Markdown artifacts. There are no identified patterns for data exfiltration, command execution, or persistence.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external task descriptions to determine appropriate routing. While this constitutes an ingestion surface for untrusted data, the skill lacks access to high-risk tools or system-level capabilities, and its output is limited to text-based reasoning.
- Ingestion points: Input defined in the contract as "problem or task".
- Boundary markers: Absent; instructions do not specify delimiters for user input.
- Capability inventory: No subprocess calls, network operations, or file-write capabilities are requested or used.
- Sanitization: Absent; the skill relies on the agent's internal safety guardrails.
Audit Metadata