papr-rss

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes example commands that pass credentials (e.g., --password) on the command line, which would require the agent to accept and embed secret values verbatim in generated commands/outputs, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow includes papr refresh / papr subscribe / papr extract, which fetches RSS/newsletter content from user-supplied or discovered URLs and then ingests the fetched article text into the agent’s LLM context via papr read/papr extract output (outsider-authored web content).