buyer-personas

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources, creating a potential vector for indirect prompt injection attacks where malicious instructions in the data could influence the agent's behavior.
  • Ingestion points: The skill reads research data, call transcripts, CRM/deal history, win/loss notes, and survey results in SKILL.md (Step 1).
  • Boundary markers: There are no specific delimiters or instructions to ignore embedded commands within the processed research data.
  • Capability inventory: The skill is capable of appending data to the local file /context/skill-sessions.md (Step 5), which is a persistent log but does not include code execution capabilities.
  • Sanitization: The skill does not perform any validation, filtering, or sanitization on the ingested external research content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 06:36 AM
Security Audit — agent-trust-hub — buyer-personas