opportunity-identifier

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt requires extracting verbatim quotes from transcripts and outputting them with citations, so if a transcript contains API keys, passwords, or other secrets those would be reproduced verbatim by the LLM (high exfiltration risk).

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

• Third-party content exposure detected (high risk: 0.85). The required workflow ingests the runtime-provided transcript text from /research:identify-opportunities "path/to/transcript.md" ... and then extracts verbatim quotes from it; if that transcript is authored by someone other than the operating user (e.g., an interviewee/interviewer), that free-form outsider-authored prose is fed into the agent’s LLM context for analysis.