voice-note-ingest
Ingest a voice note with exact-phrasing preservation (never paraphrased). Routes content to originals/, concepts/, people/, companies/, ideas/, personal/, or voice-notes/ based on a decision tree. The user's exact words are the signal.
72%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./plugin-variants/gbrain-daily/skills/voice-note-ingest/SKILL.mdThe canonical home for this skill is voice-note-ingest in garrytan/gbrain
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The agent ingests voice notes and audio messages sent by the user via channels like Telegram or audio attachments, which constitute outsider-submitted free text or unverified user content processed through transcription.
- Repository
garrytan/gbrain
- Revision
c3e8fd2
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.