The Agent Skills Directory

[SAFE]: The skill is a comprehensive set of instructions for auditing code against privacy regulations such as GDPR, CCPA, and HIPAA. It contains no malicious code, remote execution patterns, or credential access.
[INDIRECT_PROMPT_INJECTION]: The skill has an inherent attack surface for indirect prompt injection because its primary function involves auditing untrusted source code.
Ingestion points: Files containing data retention, deletion logic, and consent management are read based on the --scope flag defined in SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions within the audited content.
Capability inventory: The skill involves file reading and text reporting; no capabilities for network access, file writing, or shell command execution are requested or utilized.
Sanitization: No sanitization or escaping of content from the audited files is described.

non-compliance