meeting-insights-analyzer

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly instructs the agent to extract and include verbatim quotes from meeting transcripts (e.g., "> [Actual quote from transcript]") and to scan local transcript files, so any secrets spoken or pasted into those transcripts (API keys, passwords, tokens) would be output verbatim by the LLM.

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

• Third-party content exposure detected (high risk: 0.85). This skill’s required workflow instructs scanning a user-provided local folder for transcript files and then using their “actual quote from transcript” content as examples, meaning LLM context ingestion will include outsider-authored meeting/free-text transcript content whenever the transcript includes other participants’ speech.