product-marketing-context

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through its 'Auto-draft from codebase' feature.
  • Ingestion points: The agent reads multiple files within the local repository, including README, package.json, landing pages, and marketing copy (Step 2: Gather Information).
  • Boundary markers: There are no explicit instructions or delimiters defined to ensure the agent treats the repository content strictly as data and ignores any embedded instructions.
  • Capability inventory: The skill has the capability to read files from the local filesystem and write the resulting document to .claude/product-marketing-context.md.
  • Sanitization: The skill does not implement any validation, filtering, or escaping of the content ingested from the codebase before processing it.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:31 AM