product-marketing-context
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary 'Auto-draft' workflow relies on reading untrusted or user-provided files within the repository to generate marketing content. This creates a surface for indirect prompt injection attacks.
- Ingestion points: In
SKILL.md, Step 2 (Gather Information) specifies reading theREADME.md, landing pages, marketing copy, andpackage.jsonto extract context. - Boundary markers: The instructions do not mandate the use of delimiters (e.g., XML tags or backticks) or explicit 'ignore embedded instructions' warnings when the agent processes these external file contents.
- Capability inventory: The skill possesses the capability to read any file in the repository and write to
.agents/product-marketing-context.md. - Sanitization: There is no evidence of sanitization or filtering applied to the content read from the codebase before it is used to influence the drafting process.
Audit Metadata