sales-graphy
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill maintains a persistent knowledge mechanism through
references/learnings.md. The agent is instructed to read from and append new information to this file, which creates a potential surface for indirect prompt injection if malicious data from a user session is processed and saved for future use. - Ingestion points: The skill reads
references/learnings.mdin Step 1 to gather context. - Boundary markers: There are no specific boundary markers or instructions to ignore embedded commands within the ingested text.
- Capability inventory: The skill provides functional code templates and can route the agent to other domain-specific skills.
- Sanitization: The instructions do not define any sanitization or validation logic for data appended to the learning file.
- [EXTERNAL_DOWNLOADS]: The skill documentation references an installation command
npx skills add sales-skills/salesto add a related routing skill. This is a standard package installation from the skill's author.
Audit Metadata