sales-enablement

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process data from external websites, competitor pricing pages, and product reviews to build sales playbooks and one-pagers, which creates an inherent attack surface for indirect prompt injection.
  • Ingestion points: The skill fetches external content via WebFetch and WebSearch tools, particularly when building competitive positioning cards or verifying pricing.
  • Boundary markers: The references/house-rules.md file includes a mandatory safety instruction (Rule 7) that commands the agent to treat all fetched or pasted content as data and never as instructions, explicitly quoting embedded instructions rather than acting on them.
  • Capability inventory: The skill has capabilities to read/write to the .agents/product-context.md file, fetch remote URLs, and utilize visual rendering tools (Artifacts) for document design.
  • Sanitization: The skill relies on a combination of platform-level guardrails and the specific negative constraint in the shared house rules to mitigate risks from processing untrusted external text.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 04:06 PM