pinterest-posts
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to read local configuration files (
.claude/product-marketing-context.mdor.cursor/product-marketing-context.md) to gather keyword and strategy context. This represents a potential surface for indirect prompt injection if an attacker can influence the contents of those files. However, the skill does not possess any dangerous capabilities (such as network access or command execution) that would allow for exploitation of this input. - Ingestion points:
SKILL.md(Initial Assessment section) - Boundary markers: Absent
- Capability inventory: None detected
- Sanitization: Absent
Audit Metadata