product-marketing-context
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local codebase (README, marketing copy, package.json) to auto-draft a marketing context document.
- Ingestion points: Local codebase files including README, landing pages, marketing copy, and package.json as specified in Step 2 of the workflow.
- Boundary markers: Absent; the skill does not use specific delimiters or instructions to ignore embedded prompts within the ingested files.
- Capability inventory: The skill is restricted to reading local files and writing to the .claude/product-marketing-context.md file; it has no network access or command execution tools.
- Sanitization: Absent; content from the codebase is drafted into the target document without explicit sanitization or filtering.
Audit Metadata