research-curator
Orchestrate research entry lifecycle in ./research/ — create, batch-import, refresh stale entries, and validate structure. Use when asked to add a tool, research a URL, document a library, refresh research, validate entries, or given any tool or library URL. Supports --batch (parallel multi-URL), --rerun (refresh one or all entries), and --validate (structural check with auto-fix of error-severity issues).
71
88%
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
Low
Low-risk findings.
2 low severity findings. 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
SKILL.md’s Default Mode/Batch Mode parses attacker-supplied URLs from `<mode_args/>`, then spawns `@research-curator` with the prompt “Research and create an entry for: {URL}”, which at runtime causes the LLM to ingest outsider-authored content from those URLs to produce the research entry.
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 orchestrator accepts arbitrary URLs from <mode_args/> and --batch and injects them into agent prompts (e.g., "Research and create an entry for: {URL}") and explicitly treats provided Mermaid/process diagrams as authoritative executable procedures (example runtime URLs shown: https://url1.com, https://url2.com, https://url3.com, https://url.com), so external content at those URLs can directly control agent behavior at runtime.
- Repository
- Jamie-BitFlight/claude_skills
- Commit
c337daf
- 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.