influencer-marketing
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read local project configuration files (e.g.,
.claude/project-context.md) to align its advice with the user's specific product and audience. This creates a surface for indirect prompt injection if those files contain malicious instructions. However, the risk is negligible as the skill possesses no dangerous capabilities such as network access, file writing, or command execution. - Ingestion points: SKILL.md (references project-context files).
- Boundary markers: Absent.
- Capability inventory: None detected.
- Sanitization: None detected.
Audit Metadata