product-marketing-context
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs expected file operations within the local repository to gather marketing context. It scans standard files like README.md and package.json to assist the user, which is a legitimate and safe behavior for a development-focused agent skill.- [SAFE]: No network activity, credential harvesting, or unauthorized privilege escalation commands were detected in the skill instructions or metadata.- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface through its codebase 'auto-draft' feature. Evidence chain: 1. Ingestion points: Reads README, landing pages, marketing copy, and package.json as described in SKILL.md Step 2. 2. Boundary markers: Absent. 3. Capability inventory: File system read and write access for context management. 4. Sanitization: Absent. While this allows external data to influence the agent's drafting logic, the risk is localized to the generated documentation.
Audit Metadata