marketing-psychology
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill is entirely instructional and does not contain any executable scripts, command line invocations, or network requests. No patterns of prompt injection, obfuscation, or persistence were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest local project context to personalize its recommendations.
- Ingestion points: The skill instructs the agent to read context from .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md if present (SKILL.md).
- Boundary markers: No specific delimiters or boundary instructions are defined to separate the ingested context from the core instructions.
- Capability inventory: The skill possesses no capabilities beyond text generation; it has no access to tools for file writing, network communication, or system execution.
- Sanitization: No sanitization or validation logic is applied to the ingested context files, as they are expected to be local configuration files provided by the user.
Audit Metadata