commafeed-api

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill tells the agent to ask the user for COMMAFEED_USER/COMMAFEED_PASS if environment variables are missing and the examples/commands embed those credentials directly in curl commands (e.g. -u "$COMMAFEED_USER:$COMMAFEED_PASS"), which forces the LLM to handle and potentially output secrets verbatim.

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and ingests arbitrary public feed/web content (e.g., /rest/feed/fetch for probe-by-URL and /rest/category/entries which returns entry.content and entry.url from external RSS feeds) and the SKILL.md shows workflows and example code that read those entries and then perform follow-up actions (e.g., choosing entries to star or subscribing based on fetched feed info), so untrusted third-party content can influence tool use and next actions.