The Agent Skills Directory

[SAFE]: No malicious instructions, code obfuscation, or unauthorized data access patterns were identified. All operations are consistent with the skill's purpose of reviewing academic drafts.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes user-provided paper drafts. Ingestion points: Paper drafts accessed via the read_file tool. Boundary markers: No explicit delimiters or 'ignore embedded instruction' warnings are present. Capability inventory: The agent has permissions to read and write files using provided tools. Sanitization: No sanitization or validation of the ingested paper content is defined.

paper-review