felo-content-to-slides

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

• Third-party content exposure detected (high risk: 0.90). This skill (SKILL.md) explicitly fetches content from arbitrary webpages and YouTube videos (via the --url and --video options) and then reads and uses those untrusted third-party transcripts/pages to generate PPTs, so external page or video content could inject instructions that affect output generation.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill fetches arbitrary webpage or YouTube content at runtime (for example the CLI usage with https://openclaw.ai/) and injects that fetched content into the model's context to generate slides, so remote content can directly control the agent's prompts.