sparkfinderoven-security-compliance-skills

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

• Third-party content exposure detected (high risk: 0.75). The skill suite’s runtime workflows shown (e.g., /dep-cve with sources nvd, github-advisories, snyk, and any vendor/interactive workflows) can fetch public third-party advisory text at runtime and feed it into the agent’s LLM context, which is outsider-authored free-form content via external web/API responses.

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

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