press-kit
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed of markdown instructions and basic configuration files. Analysis found no evidence of prompt injection, obfuscation, or malicious command execution.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing user requests and reading a local configuration file (.agents/marketing-context.md). Ingestion points: User input and marketing-context.md referenced in SKILL.md. Boundary markers: None present. Capability inventory: Text generation only; no dangerous tools (e.g., shell access, network requests) are invoked. Sanitization: None present.
Audit Metadata