product-marketing-context
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it is instructed to scan and read the content of various files in the user's repository to generate a marketing draft.
- Ingestion points: The workflow in
SKILL.mdexplicitly instructs the agent to read the codebase, including the README, landing pages, marketing copy, about pages, meta descriptions,package.json, and 'any existing docs'. - Boundary markers: The instructions do not specify any boundary markers or delimiters to help the agent distinguish between its instructions and the data found within the scanned files.
- Capability inventory: Across the provided files, the skill's capabilities include reading files from the repository and writing a summarized context file to
.agents/product-marketing-context.md. It does not demonstrate network access or arbitrary command execution. - Sanitization: No sanitization, filtering, or validation logic is defined for the content extracted from the repository files before it is processed to create the marketing context.
Audit Metadata