content-strategy
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external data sources, creating a potential surface for indirect prompt injection. \n
- Ingestion points: The skill processes scraped page text, customer reviews, comments, emails, and third-party exports as noted in the 'Data Sources' section of SKILL.md. \n
- Boundary markers: The skill includes defensive instructions in both the 'Skill Contract' and 'Data Sources' sections, explicitly telling the agent to treat these sources as untrusted input and to ignore any instructions found within the data. \n
- Capability inventory: The skill framework allows for optional integrations with established marketing, search, and RevOps tools (e.g., Google Ads, HubSpot, Salesforce, Stripe) as described in references/connectors.md, which could be misused if an indirect prompt injection were successful. \n
- Sanitization: The skill relies on behavioral instructions for the agent to filter data; it does not specify programmatic sanitization or strict schema validation for the raw external inputs mentioned.
Audit Metadata