pp-zoom

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's examples and commands show embedding Zoom meeting URLs with unencrypted passwords and instruct creating/persisting meeting IDs/passwords (and delivering output via webhooks), which requires the agent to include secret values verbatim in generated CLI commands or outputs, posing an exfiltration risk.

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

• Third-party content exposure detected (low risk: 0.10). In SKILL.md, the runtime workflow for “zoom-pp-cli find/notes search/notes todos/recordings export/notes transcript/notes summary” can ingest the user’s own Zoom transcripts, meetings, and exported Notes PDFs/DOCX (and fetches meeting summaries/transcripts from Zoom’s OAuth-gated endpoints), but there is no described path where outsider-authored free text can be posted into a queue/feed for the agent to read without the agent selecting specific content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's Prerequisites include an installation step "go install github.com/mvanhorn/printing-press-library/library/productivity/zoom/cmd/zoom-pp-cli@latest" which, if executed at runtime, fetches and builds remote code that the skill requires to run (github.com/mvanhorn/printing-press-library/library/productivity/zoom/cmd/zoom-pp-cli@latest).