product-marketing-context

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection during its codebase analysis workflow.
  • Ingestion points: In Step 2, the agent is instructed to read various files from the codebase, including READMEs, landing pages, and marketing copy, which are potential vectors for hidden malicious instructions.
  • Boundary markers: The skill does not provide the agent with delimiters or instructions to ignore embedded commands within the files it reads.
  • Capability inventory: The skill has the capability to read local project files and write the generated marketing context to the .claude/product-marketing-context.md file.
  • Sanitization: There is no logic specified to sanitize or validate the content retrieved from external files before it is used to populate the marketing document.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 01:22 PM