social-content
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes an ingestion surface for potentially untrusted data. \n
- Ingestion points: The skill reads context from
.claude/product-marketing-context.mdas specified inSKILL.md. \n - Boundary markers: No specific delimiters or warnings for the agent to ignore instructions within the context file are provided. \n
- Capability inventory: The skill possesses no dangerous capabilities such as command execution, file-writing, or network operations. \n
- Sanitization: No data sanitization or validation is implemented for the ingested context. \n- [SAFE]: Beyond the described data ingestion surface, the skill consists purely of markdown-based strategic guidance and post templates for social media managers. It does not include any scripts or automation that could be misused.
Audit Metadata