public-relations

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains static instructional content for public relations, including templates for press releases and guidelines for writing styles. It does not contain any code, command execution, or network operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to read project-specific metadata from .claude/project-context.md or .cursor/project-context.md to tailor its output to the user's business context. While this involves processing external data, the skill uses this information solely for text generation and lacks any capabilities (such as file writing or network access) that could be exploited through malicious data in those files. This implementation follows standard best practices for agent-based project awareness.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 10:32 AM