paid-ads
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill acts as a comprehensive strategic guide for performance marketing. It contains only text-based instructions and references to internal markdown templates, with no evidence of command execution or external data exfiltration.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by instructing the agent to ingest external context.
- Ingestion points: The instruction in SKILL.md to read .claude/product-marketing-context.md before starting.
- Boundary markers: No delimiters or instructions to ignore embedded commands are present for the context file.
- Capability inventory: No dangerous capabilities (such as subprocess calls, file writing, or network access) are present in the skill or its referenced files.
- Sanitization: No validation or sanitization is performed on the ingested context.
- Verdict Note: While the attack surface exists, the risk is negligible as the skill lacks any capabilities that could be abused via an injection attack.
Audit Metadata