competitive-analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow is to compile competitive analyses using “publicly available information” such as competitor websites/documentation and review sites (e.g., G2/TrustRadius), which are outsider-authored free text that can be ingested into the LLM context via fetched web pages or scraped review content.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)