sales-front
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill implements a persistent 'learnings' mechanism that reads from and appends to
references/learnings.md. This creates an indirect prompt injection surface where instructions or data encountered during a session could be saved and subsequently trusted in future sessions. - Ingestion points: The skill reads
references/learnings.mdat the start of Step 1 to gather context. - Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the ingested learning content.
- Capability inventory: The skill has the capability to append new content to
references/learnings.mdbased on discoveries during the session. - Sanitization: There is no evidence of validation or sanitization of the content before it is appended to the learnings file.
Audit Metadata