playbook-pr-publicity
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is purely instructional and serves as a template for generating professional PR documents. It does not contain any executable logic or scripts.
- [NO_CODE]: No scripts, shell commands, or external dependencies are included. The functionality relies entirely on the agent's natural language generation based on the provided templates.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a clear ingestion surface for user-provided data, but the risk is negligible due to the lack of exploitable capabilities.
- Ingestion points: The 'Required Input' section in
SKILL.mdprompts for client-specific data such as business names and industries. - Boundary markers: Not explicitly defined in the prompts.
- Capability inventory: No file system access, network operations, or shell execution capabilities are present in the skill.
- Sanitization: Not implemented, as the output is intended for standard text-based PR documents.
Audit Metadata