content-as-product
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information to generate content topics, hooks, and follow-up scripts, which presents a surface for potential instruction injection.
- Ingestion points: User requests for content creation, topics, and marketing hooks in SKILL.md.
- Boundary markers: The instructions lack explicit delimiters or warnings to treat user-provided content topics as untrusted data.
- Capability inventory: The skill involves generating text and image prompts and reading external methodology files from the
../../../../knowledge/directory. - Sanitization: There is no evidence of sanitization, filtering, or escaping of user-provided content before it is interpolated into the agent's generation process.
Audit Metadata