offer-positioning
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of markdown files and a metadata manifest. No code, scripts, or binary executables are present, and the skill performs no network operations or sensitive file access.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information to generate messaging directions, creating a surface for potential indirect prompt injection. 1. Ingestion points: User-provided arguments for product/service, target customer, and business goal (SKILL.md). 2. Boundary markers: No explicit delimiters or instructions are provided to the agent to treat input as untrusted data. 3. Capability inventory: The skill is limited to the use of the Read and Write tools (SKILL.md). 4. Sanitization: No input validation or content filtering is defined in the instructions.
Audit Metadata