The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The skill's behavior aligns with its stated purpose of evaluating research artifacts.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it is designed to ingest and semantically analyze untrusted research artifacts. This is a functional requirement of its primary purpose as a reviewer.
Ingestion points: SKILL.md (Step 1) defines a sequence for reading multiple files including PAPER.md, logic/claims.md, logic/experiments.md, and other files within an external artifact directory.
Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' instructions when processing the content of the research artifacts.
Capability inventory: The skill's operations are limited to native file tools (Read, Write, Glob, Grep) as specified in the SKILL.md instructions.
Sanitization: Absent. No explicit sanitization or filtering logic is provided for the ingested artifact content.

ara-rigor-reviewer