product-marketing
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze external or user-provided data (codebase, landing pages, marketing copy, meta descriptions) to draft a product marketing context document. This process lacks explicit safeguards to prevent the agent from obeying instructions that might be hidden within that data.
- Ingestion points: Instructions in
SKILL.md(Step 2) direct the agent to read the repository README,package.json, landing pages, marketing copy, about pages, and meta descriptions. - Boundary markers: The skill does not specify the use of delimiters (e.g., XML tags or backticks) or provide explicit 'ignore embedded instructions' warnings for the data being analyzed.
- Capability inventory: The skill is designed to perform file system write operations by creating and updating the
.agents/product-marketing.mdfile. - Sanitization: There is no mention of filtering, escaping, or validating the ingested content before it is processed by the agent to generate the marketing draft.
Audit Metadata