competitive-battlecard-creation
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's workflow requires the agent to research competitor products by gathering intelligence from external, untrusted sources including their websites, changelogs, job postings, and third-party review sites like G2 or Gartner. This creates a surface for indirect prompt injection, where an attacker could place hidden instructions on these pages to manipulate the agent's output or steering logic.
- Ingestion points: External web content as described in 'Workflow Step 1' (Competitor website, changelog, job postings, review sites).
- Boundary markers: The skill does not instruct the agent to use specific delimiters or boundary markers to separate external data from its own instructions.
- Capability inventory: The skill implies the use of web browsing or search tools to gather the necessary intelligence.
- Sanitization: The instructions do not include steps to sanitize, validate, or filter the content retrieved from external sources.
Audit Metadata