marketing-ideas
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill instructions direct the agent to read local project files (e.g., '.agents/product-marketing.md', '.claude/product-marketing.md') to gather context, which introduces a surface for indirect prompt injection.
- Ingestion points: Context files identified in SKILL.md used to inform marketing strategy recommendations.
- Boundary markers: Absent; there are no instructions to the agent on how to distinguish between legitimate marketing context and potential malicious instructions within the files.
- Capability inventory: None; the skill does not possess tools for network access, file system modification, or command execution.
- Sanitization: Absent; the skill does not specify any validation, escaping, or filtering for the content of the context files.
- [NO_CODE]: The skill consists entirely of natural language instructions and a static markdown reference list. It contains no scripts, binaries, or third-party code dependencies.
Audit Metadata