sales-tableau

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection vulnerability surface.
  • Ingestion points: User-provided descriptions of Tableau issues and licensing questions enter the agent's context as specified in SKILL.md.
  • Boundary markers: Delimiters and instructions to ignore embedded commands are absent when the agent processes user input or reads from references/learnings.md.
  • Capability inventory: The agent has the capability to append content to references/learnings.md (SKILL.md Step 4), which is subsequently read by the agent at the start of every session (SKILL.md Step 1). This creates a persistent channel where untrusted user input can influence future agent behavior.
  • Sanitization: There is no evidence of sanitization, validation, or escaping of user-provided content before it is stored in the local learning file.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 06:35 PM