ara-rigor-reviewer
Performs ARA Seal Level 2 semantic epistemic review on Agent-Native Research Artifacts, scoring six dimensions (evidence relevance, falsifiability, scope calibration, argument coherence, exploration integrity, methodological rigor) and producing a constructive, severity-ranked report with a Strong Accept-to-Reject recommendation. Use after Level 1 structural validation passes, when an ARA needs an objective epistemic critique before publication or release.
67
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill explicitly requires quoting exact substrings from artifact files as evidence_span in findings, which forces the LLM to output verbatim content from local files and therefore could exfiltrate any secrets contained there.
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
The required workflow reads the ARA’s contents at runtime—explicitly including outsider-authored free-text files like `PAPER.md`, `logic/*.md`, `trace/exploration_tree.yaml`, and `evidence/*`—and then places that parsed prose into the LLM context for semantic review, creating an indirect prompt-injection exposure path (even though it forbids URL fetching/execution).
- Repository
- Orchestra-Research/AI-Research-SKILLs
- Commit
773a529
- 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.