skills/jeremylongshore/tons-of-skills-marketplace/scanning-for-data-privacy-issues/Gen Agent Trust Hub
scanning-for-data-privacy-issues
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions are aligned with its primary purpose of privacy auditing. It uses standard regex patterns and shell utilities to identify potential PII exposure in logs, code, and databases without attempting to bypass safety filters or exfiltrate data.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code and configuration files, which presents a surface for indirect prompt injection where adversarial comments in the scanned data could attempt to influence the agent's behavior.
- Ingestion points: Application source code, logs, and configuration files located in the ${CLAUDE_SKILL_DIR} directory.
- Boundary markers: No specific delimiters or boundary markers are defined to isolate untrusted content from the agent's instructions.
- Capability inventory: The skill is permitted to use Read, Write, Edit, Grep, Glob, and Bash tools.
- Sanitization: No specific sanitization or filtering of input content is described in the processing instructions.
Audit Metadata