sales-enablement

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides comprehensive instructional content and templates for B2B sales enablement tasks such as creating sales decks, one-pagers, and objection handling documents. No malicious patterns or security risks were identified.
  • [NO_CODE]: The skill is composed entirely of Markdown documentation and a JSON evaluation file. There are no scripts, binaries, or instructions that trigger shell execution or code interpretation.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes an instruction to ingest data from an external file (.agents/product-marketing-context.md). While this constitutes a data ingestion surface, the risk is mitigated by the lack of exploitable capabilities.
  • Ingestion points: Reads project-specific context from .agents/product-marketing-context.md (documented in SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: None; the skill does not use shell commands, network requests, or file-writing operations.
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 06:49 PM
Security Audit — agent-trust-hub — sales-enablement