sales-attio
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill implements a persistent state mechanism by reading from and writing to references/learnings.md. This architecture presents a surface for indirect prompt injection, where data gathered in one session might influence the agent's behavior in subsequent sessions.
- Ingestion points: The file references/learnings.md is read during the initial context gathering phase in SKILL.md.
- Boundary markers: There are no explicit markers or instructions to treat the content of learnings.md strictly as data rather than instructions.
- Capability inventory: The agent is instructed to append new observations to references/learnings.md in the 'Gotchas' section of SKILL.md.
- Sanitization: No sanitization process is defined for the information written to or retrieved from the persistent storage.
Audit Metadata