skillify
Codify the most recent successful /scrape flow into a permanent browser-skill on disk. (gstack)
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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
In `skillify` Step 1, the workflow walks back through the conversation to find the most recent successful `/scrape` (and later uses that accepted scrape’s captured JSON/intent plus `$B`-produced fixture HTML), which is outsider-authored free text injected through prior user/chat messages and then ingested for synthesis.
- Repository
- garrytan/gstack
- Commit
d078622
- 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.