instagram-video-downloader

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill includes concrete examples that embed API keys directly into export commands, command-line arguments, and config-file writes, which would require the LLM to output secret values verbatim if it generates those commands.

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

• Third-party content exposure detected (high risk: 0.70). The runtime workflow calls an outsider-controlled public API (redfox.hk) and then prints data.get("desc") and other returned fields as readable text to stdout; if those fields contain free-form text, they are fed into the agent’s LLM context via the skill’s output.