specialist-engineering-compliance-auditor
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses a template that interpolates untrusted user input directly into the instructions for a spawned sub-agent, creating a surface for indirect prompt injection.
- Ingestion points: User-provided input via the {the user's question} variable in SKILL.md.
- Boundary markers: Absent; there are no delimiters (e.g., XML tags or triple quotes) to separate user content from the agent's instructions.
- Capability inventory: The skill has the ability to spawn ephemeral sub-agents via the Agent tool.
- Sanitization: No sanitization or escaping of the user-provided string is performed before interpolation.
Audit Metadata