product-marketing-context
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill manages local documentation and context within the project's directory. While it reads files such as README.md and package.json to auto-draft marketing content, this surface for indirect prompt injection is mitigated by the skill's limited scope (generating markdown) and lack of high-risk capabilities like network access or arbitrary code execution.
- Ingestion points: The skill reads local files including README, package.json, and other project documentation.
- Boundary markers: No specific delimiters are defined in the instructions for content ingestion.
- Capability inventory: The skill is restricted to local filesystem read and write operations within the .agents/ and .claude/ directories.
- Sanitization: Ingested content is used for drafting without explicit sanitization, which is standard for documentation-building tasks.
Audit Metadata