add-talk
Add new conference talks to the talks portfolio repository. Handles fetching metadata from sched.co URLs or manual input, generating talk directories with README.md files, fuzzy-matching slide PDFs from ~/Downloads/, and staging all changes. Use when user says "add talk", "new talk", "add these talks", provides sched.co URLs, or mentions adding a presentation or conference entry.
89%
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
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’s Step 1 “Fetch from sched.co” uses each user-provided sched.co/sched.com URL to curl and then extracts the `<script type="application/ld+json">` block (including title/description/location) from the fetched HTML at runtime, so outsider-authored text can be ingested via posted URLs.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill explicitly fetches user-provided sched.co URLs at runtime with curl and extracts the page's JSON-LD (sched.co / sched.com), which is then parsed to populate and control the generated README content, so external page content directly influences agent output.
- Repository
jpkrohling/talks
- Revision
bd20936
- 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.