launch
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions, marketing frameworks (like ORB), and planning checklists. It does not include scripts, shell commands, or remote dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill is instructed to read local context files (e.g.,
.agents/product-marketing.md) to inform its marketing advice. While this constitutes an ingestion surface for untrusted data, the skill has no functional capabilities (such as network access, file writing, or command execution) that could be used to exploit this surface. - Ingestion points: .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md referenced in SKILL.md.
- Boundary markers: Absent; the agent is simply told to read the files.
- Capability inventory: None; no tools or dangerous primitives are enabled or utilized by the skill.
- Sanitization: Absent; the skill relies on the underlying LLM's default processing.
Audit Metadata