founder-marketing
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from several local files that are likely to contain information gathered from external sources or research, creating a surface for indirect instructions to be processed by the agent.
- Ingestion points: The skill reads founder/panel/results.md, founder/competitors.md, founder/offer.md, founder/pricing.md, and founder/numbers.json to generate positioning and campaign details.
- Boundary markers: There are no explicit delimiters or specific instructions (e.g., 'treat the following as data only') to prevent the agent from obeying commands that might be hidden within the buyer panel results or competitor descriptions.
- Capability inventory: The skill has the capability to write to the file system (founder/marketing.md) and triggers follow-up actions with other skills.
- Sanitization: There is no evidence of content sanitization, filtering, or validation before the external data is interpolated into the marketing output.
Audit Metadata