qa-do
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill functions strictly as an informational router for QA tasks. It provides a comprehensive lookup table and decision logic to help users select specialized skills for testing, automation, and infrastructure. No malicious patterns, command executions, or external dependencies were found in the instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input via the
$ARGUMENTSvariable to provide recommendations. While this is an entry point for potential indirect prompt injection, the risk is negligible because the skill does not possess high-privilege capabilities such as file modification, network exfiltration, or code execution. The output is purely advisory. - Ingestion points: User-provided descriptions of QA situations (SKILL.md).
- Boundary markers: None explicitly defined for the argument interpolation.
- Capability inventory: No subprocess calls, network operations, or file-system writes are present in the skill.
- Sanitization: None detected; the skill relies on the LLM to interpret the routing table based on natural language input.
Audit Metadata