discovery
Capture interesting finds to the Vault via Inngest. Triggers when the user shares a URL, repo, or idea with signal words like "interesting", "cool", "neat", "check this out", "look at this", "came across", or when sharing content with minimal context that implies it should be remembered. Also triggers on bare URL drops with no explicit ask. Fires a discovery/noted event and continues the conversation — the pipeline handles everything else.
68
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Security
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
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
Third-party content exposure detected (high risk: 0.85). The required runtime workflow (`joelclaw send discovery/noted --follow`) triggers the `discovery/enrich` pipeline, which fetches and extracts readable content from outsider-provided URLs (e.g., arbitrary web pages or repo content) and then writes that text into the LLM-generated discovery note context.
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
Potentially malicious external URL detected (high risk: 0.90). The Inngest enrichment pipeline and background "Investigate" step fetch remote content at runtime—cloning repos (e.g., tracked repos like anomalyco/opencode on GitHub) and fetching articles/tweets (e.g., GET https://api.twitter.com/2/tweets/:id and source article URLs via defuddle)—and that fetched content is injected into the "pi" model to generate summaries, so external URLs directly influence agent prompts and outputs.
- Repository
- joelhooks/joelclaw
- Commit
2ca3686
- 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.