auto-categorize
Quick-capture raw text, a URL, or conversational content into a classified vault note — no interactive prompts. Triggers: "save this as a note", "clip this", "add this to the vault", "categorize this", "turn this into a note", "I found this useful, save it".
73
90%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
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 workflow allows fetching and ingesting arbitrary URLs via WebFetch, which constitutes outsider-authored content that the agent actively retrieves.
- Repository
- seanGSISG/claude-depot
- Commit
48bf6a4
- 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.