sales-calabrio
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection surface via persistent learning mechanism. The skill reads from references/learnings.md at startup and appends new content to it at the end of a session, which could allow malicious instructions provided in one session to influence the agent in future sessions.
- Ingestion points: references/learnings.md is read at the start of every session to gather platform knowledge.
- Boundary markers: The skill does not use specific delimiters or instructions to treat the ingested data as untrusted.
- Capability inventory: The agent can provide configuration guidance, API integration steps, and troubleshooting advice based on the ingested content.
- Sanitization: No sanitization is performed on user-provided tips or gotchas before they are persisted to the learnings file.
- [EXTERNAL_DOWNLOADS]: Fetches and references official integration samples, documentation, and Postman collections from the vendor's official GitHub organization and official websites.
Audit Metadata