The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were detected in the skill's instructions or configuration.
[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection because it reads and processes the content of arbitrary files provided by the user via the Read tool. However, the risk is minimal as the skill lacks network or write capabilities to exfiltrate data or cause persistent system changes.
Ingestion points: The skill reads file contents specified in the $ARGUMENTS using the Read tool (SKILL.md).
Boundary markers: There are no explicit delimiters or instructions to ignore instructions embedded within the files being proofread.
Capability inventory: The skill is restricted to the Read tool and text generation; no subprocess, network, or file-writing tools are allowed.
Sanitization: No sanitization of the file content is performed before processing.

proofreader