sales-methodology

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill consists exclusively of Markdown documentation and text-based instructional templates. No scripts, binaries, or automated tool configurations are present, which eliminates the risk of unauthorized code execution.
  • [PROMPT_INJECTION]: The skill instructs the agent to analyze external 'unstructured data' such as sales call transcripts and CRM history to perform deal scoring (documented in SKILL.md and references/emerging-practices-ai-augmented-methodology.md). This is an indirect prompt injection surface. * Ingestion points: The workflow identifies call transcripts (e.g., Gong, Fireflies), CRM history, and external firmographic data (e.g., Apollo, 6sense) as inputs. * Boundary markers: No explicit delimiters or isolation instructions are provided for these external inputs. * Capability inventory: The agent's capabilities are restricted to text analysis, scoring, and coaching based on the input. * Sanitization: The instructions do not define filtering or sanitization steps for transcript data.
  • [SAFE]: The documentation mentions external services and tools for enrichment (e.g., 6sense, Apollo, Gong) and links to the author's site (neontriforce.com). These are standard industry references and do not involve suspicious data exfiltration or credential harvesting.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 02:35 PM
Security Audit — agent-trust-hub — sales-methodology