sales-content
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill implements a persistent 'learnings' mechanism that reads from
references/learnings.mdat the start of each session and appends new information to it. This creates a surface for indirect prompt injection where malicious instructions could be stored and later executed by the agent.\n - Ingestion points:
references/learnings.md(read at startup).\n - Boundary markers: None identified in the instructions for the ingested content.\n
- Capability inventory: The skill possesses file-write capabilities to
references/learnings.md.\n - Sanitization: No sanitization or validation is performed on the data being appended or read from the file.\n- [EXTERNAL_DOWNLOADS]: The documentation includes an instruction for the user to execute
npx skills add sales-skills/sales --skills sales-do. This command fetches and installs additional components from the developer's package repository.
Audit Metadata