customer-story-builder
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection because it processes untrusted external data that could contain malicious instructions.
- Ingestion points: Raw customer inputs defined in Phase 0 (SKILL.md), including interview transcripts, Slack quotes, support ticket excerpts, and survey responses.
- Boundary markers: Absent. The instructions do not define delimiters or provide specific warnings to the agent to ignore embedded instructions within the processed data.
- Capability inventory: The skill instructs the agent to perform file-write operations in Phase 4 (SKILL.md) to save assets to the
clients/directory. - Sanitization: Absent. There is no logic provided to sanitize or validate the content of the raw inputs before they are interpolated into the prompt templates.
Audit Metadata