ielts-study-plan
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill performs its primary operations by calling a bundled Python script,
scripts/ielts_buddy_api.py, which serves as the interface to the backend API. - [INDIRECT_PROMPT_INJECTION]: The skill processes content retrieved from the IELTS Buddy API, including study materials and user activity logs, which serves as a potential vector for indirect prompt injection. 1. Ingestion points: The
ielts_prep_read_guideandielts_learner_export_datafunctions ingest external text into the agent context as described inSKILL.mdandreferences/setup.md. 2. Boundary markers: The instructions do not define specific delimiters or include directives for the agent to disregard instructions potentially embedded within the fetched study content. 3. Capability inventory: The skill is capable of executing shell commands via the provided script and performing local file system writes for data caching. 4. Sanitization: There is no specification in the skill documentation for validating or sanitizing the content received from the remote API. - [EXTERNAL_DOWNLOADS]: The skill communicates with
work.ieltsbuddy.igopx.cnandieltsbuddy.igopx.cnto access user learning data and service configuration. These endpoints are official service domains for the IELTS Buddy tool developed by the skill author.
Audit Metadata