sales-enablement

Pass

Audited by Gen Agent Trust Hub on Nov 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and incorporate content from local project files (e.g., .agents/product-marketing.md, product-marketing-context.md) to tailor its sales collateral output. While this creates a potential ingestion surface for indirect instructions, it is fundamental to the skill's intended functionality. * Ingestion points: Referenced in SKILL.md under the 'Before Starting' section. * Boundary markers: No delimiters or warnings are used to separate ingested context from the skill's core instructions. * Capability inventory: The skill's actions are restricted to generating textual sales content; it does not contain tools for command execution, network requests, or file system modifications. * Sanitization: No input validation or sanitization is performed on the ingested content.
  • [NO_CODE]: This skill consists entirely of Markdown instructions and reference templates. It does not include any executable scripts or binary files, significantly reducing the potential for malicious logic execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 1, 2026, 02:17 PM