The Agent Skills Directory

[SAFE]: The skill provides legitimate documentation and utilities for software development. No malicious patterns or security risks were identified in the skill instructions or the provided analysis script.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes user-provided source code. 1. Ingestion points: Code snippets or files provided by the user for review. 2. Boundary markers: None explicitly defined to separate code from instructions. 3. Capability inventory: The skill utilizes static analysis via the review.py script (reading files and parsing AST) and the agent's general knowledge; it does not execute the reviewed code. 4. Sanitization: The use of ast.parse in review.py ensures the code is treated as data for structural analysis rather than executable logic, mitigating injection risks.

pyside6-reviewer