gog-meeting-prep
Google Calendar meeting preparation with gog, including attendees and linked Workspace files.
62
78%
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 ./.agents/skills/gog-meeting-prep/SKILL.mdW011: 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
Runtime path: the skill instructs the agent to fetch Calendar events and Drive/Docs file text via `gog ... calendar events ... --json --wrap-untrusted` and `gog ... drive get ... --json --wrap-untrusted` / `gog ... docs cat ... --json --wrap-untrusted`, which would ingest outsider-authored free text from external calendar/docs content into the LLM context (even if treated as untrusted, it is still fed to the model).
- Repository
- openclaw/gogcli
- Commit
414e2ff
- 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.