tw-stu-vocab-builder
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted user-supplied data for literary analysis in the 'Guided Reading Practice' module.
- Ingestion points: External text provided by the user is ingested for processing in Step 4 of the
SKILL.mdfile. - Boundary markers: The instructions lack explicit boundary markers (e.g., XML tags or delimiters) to separate user data from the agent's instructional context.
- Capability inventory: The skill's execution environment includes access to
Bash,Read, andWritetools as specified in theSKILL.mdfrontmatter. - Sanitization: There are no instructions or mechanisms provided to sanitize or validate the user-provided text before the agent performs its analysis.
Audit Metadata