product-marketing-context
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFE
Full Analysis
- [Data Exposure] (SAFE): The skill accesses repository files such as README, landing pages, and package.json to generate marketing content. This is consistent with its intended purpose and does not target sensitive system or credential files.
- [Indirect Prompt Injection] (LOW): The skill exhibits an attack surface for indirect prompt injection because it ingests untrusted data from the codebase to 'auto-draft' documents.
- Ingestion points: Local repository files (README, marketing copy, about pages, etc.).
- Boundary markers: Absent; the instructions do not specify delimiters or warnings to ignore instructions found within the analyzed files.
- Capability inventory: The agent has the ability to read local files and write a new markdown file to the
.claude/directory. - Sanitization: Absent; content from the codebase is processed directly into the draft.
- [Persistence] (SAFE): While the skill creates a persistent file in the
.claude/directory, this is the core functionality requested by the user and does not constitute a malicious persistence mechanism.
Audit Metadata