offers
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists exclusively of Markdown files for instruction and reference. There are no Python scripts, JavaScript files, Shell scripts, or compiled binaries, which eliminates the risk of direct command execution or code-based vulnerabilities.
- [SAFE]: No indicators of prompt injection, credential harvesting, or unauthorized data exfiltration were found. The instructions are consultative and follow standard business frameworks.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an ingestion point where it reads the file '.agents/product-marketing.md' (or variants) for context. While this allows external data into the agent's context, the skill does not possess any tools for network access, file writing, or code execution that could be exploited via injection. 1. Ingestion points: .agents/product-marketing.md (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: None (no code/tools). 4. Sanitization: Absent.
Audit Metadata