transcript-purpose-analysis

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt requires preserving and including verbatim transcript text (anchors and "short verbatim quote" evidence) so any secrets present in the transcript would be output exactly, enabling exfiltration.

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

• Third-party content exposure detected (medium risk: 0.30). The skill reads a user-supplied transcript text (either inline or from a repository path provided as input) end-to-end as the LLM’s direct input, so outsider-authored free text can be provided via the “Transcript” input.