customer-story-builder
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and summarize untrusted data from external sources like transcripts, Slack quotes, and survey responses.
- Ingestion points: Phase 0 (Intake) accepts raw transcripts, Slack/email quotes, and support ticket excerpts.
- Boundary markers: The instructions lack specific delimiters (e.g., XML tags or triple quotes) or negative constraints to prevent the agent from following instructions embedded within the customer data.
- Capability inventory: The skill is restricted to file system write operations (saving markdown files to the
clients/directory). It has no network exfiltration or command execution tools. - Sanitization: There is no explicit instruction to sanitize or escape the content before processing it into the final markdown outputs.
Audit Metadata