popups
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The content of the skill is restricted to natural language guidelines for marketing and conversion optimization, with no scripts or system-level operations.
- [INDIRECT_PROMPT_INJECTION]: The instructions direct the agent to incorporate information from local marketing context files, which represents a potential ingestion surface for indirect instructions.
- Ingestion points: Reads
.agents/product-marketing.md,.claude/product-marketing.md, orproduct-marketing-context.mdfrom the project environment. - Boundary markers: The instructions do not define specific delimiters or warnings for these files.
- Capability inventory: No file writing, network calls, or command execution tools are utilized by this skill.
- Sanitization: No sanitization or filtering is applied to the ingested content.
- [SAFE]: No obfuscation, prompt injection, or credential exposure patterns were detected in the skill instructions or metadata.
Audit Metadata