uc-interviewer
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its document processing workflow.
- Ingestion points: The skill uses a
Readtool in Phase 0.1 to ingest content from user-provided Business Requirement Documents (BRD). - Boundary markers: The prompt does not define clear delimiters or specific instructions to ignore embedded commands within the ingested BRD content.
- Capability inventory: The agent has the ability to read files, track state via
TodoWrite, interact with the user viaAskUserQuestion, and write Markdown files to the local file system. - Sanitization: No explicit sanitization or filtering of the BRD content is performed before processing; however, the skill's design requires human confirmation for every journey step and priority, which provides a significant behavioral safeguard against accidental obedience to injected instructions.
Audit Metadata