Sage Voice
v0.1.0A voice-learning writing assistant that helps you communicate in your own style — not generic AI prose. Learns how you write, adapts to your audience, and ge...
⭐ 0· 192·0 current·0 all-time
by@evanl1
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
Name/description (a voice-learning writing assistant) aligns with the instructions: building a style fingerprint and adapting output. The declared dependency on 'sage-cognitive' for profile/memory is coherent with the stated goal.
Instruction Scope
Runtime instructions explicitly tell the agent to "build a style fingerprint from the user's actual messages, emails, and documents" and to save it as a core memory in sage-cognitive. That capability is consistent with the skill's goal but is very broad and privacy-sensitive: the SKILL.md does not limit which mailboxes/files/sources to use, require explicit user consent for each source, or describe retention/visibility of the stored voice_profile.
Install Mechanism
Instruction-only skill with no install spec and no code files. Nothing will be written to disk or downloaded by an installer during install — lower technical installation risk.
Credentials
The skill requests no environment variables, credentials, or config paths. Its only persistent interaction is with the declared 'sage-cognitive' dependency (profile and core memory), which is proportionate to the functionality.
Persistence & Privilege
always:false (normal). The skill instructs saving/updating a 'voice_profile' in sage-cognitive core memory; storing user-derived fingerprints is expected for this feature but raises privacy concerns about what is stored, who can read it, retention, and whether the agent will ingest additional user data autonomously.
What to consider before installing
This skill is coherent with its stated purpose, but it asks the agent to ingest and persist private content (messages, emails, documents) without describing safeguards. Before installing, confirm: (1) exactly which sources the skill (and sage-cognitive) will access (mailboxes, files, chat history); (2) whether the agent will ask you before ingesting new sources or files; (3) how the 'voice_profile' is stored, who can read it, retention policy, and whether it's encrypted; (4) whether you can review and delete the stored profile; and (5) who maintains the dependent skill 'sage-cognitive' and its permissions. If you need stronger privacy guarantees, require explicit opt-in per data source, limit intake to user-approved examples, and audit the GitHub repo or request code/implementation details before enabling autonomous use.Like a lobster shell, security has layers — review code before you run it.
latestvk9759a7d162d3e05mrfymhqnb182na4p
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🎙️ Clawdis