review-prompt
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill interpolates untrusted user content via the $ARGUMENTS variable directly into instructions for the prompt-reviewer agent without any isolation or delimiters.
- Ingestion points: $ARGUMENTS variable in SKILL.md.
- Boundary markers: Absent; instructions and data are not separated.
- Capability inventory: Invokes the prompt-reviewer agent to process the input.
- Sanitization: None present; input is passed as-is to the downstream agent.
Audit Metadata