ielts-writing-coach
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references assessment guidelines, scoring criteria, and sample candidate responses from well-known official sources, including ielts.org, britishcouncil.org, and celpip.ca. These references are used to maintain accuracy and alignment with official standards.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-submitted writing drafts and revisions to provide feedback and drills.
- Ingestion points: User input enters the agent context via the 'Draft provided' and 'Revision provided' logic in SKILL.md.
- Boundary markers: The instructions lack specific delimiters or instructions to treat user input as purely data, which could allow a malicious draft to influence agent behavior.
- Capability inventory: The skill itself does not invoke dangerous tools (like code execution or network exfiltration), which significantly mitigates the risk of this ingestion surface.
- Sanitization: There are no requirements for the agent to sanitize or validate the user-provided text before analysis.
Audit Metadata