positioning-workshop
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection by encouraging the ingestion of untrusted external content.
- Ingestion points: In
SKILL.mdunderStep 0: Gather Context, the agent is instructed to ask the user for website copy, customer testimonials, case studies, and competitive intel. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or sanitize potentially malicious prompts embedded within the provided context (e.g., hidden instructions in a pasted testimonial).
- Capability inventory: The skill itself is purely interactive and does not appear to utilize dangerous tools like shell execution, network requests, or file system modifications.
- Sanitization: No sanitization or validation logic is present to filter the input before it is processed by the agent.
Audit Metadata