social-content
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional markdown and text templates for social media strategy. No malicious patterns or behaviors were found.
- [NO_CODE]: The skill does not contain any executable code, scripts, or platform-specific tool definitions across any of its files.
- [INDIRECT_PROMPT_INJECTION]: The reverse engineering framework suggests analyzing large amounts of external content from other creators, which is a potential surface for indirect prompt injection if that data contains malicious instructions.
- Ingestion points: External social media posts gathered from platforms like LinkedIn and Twitter as described in
references/reverse-engineering.md. - Boundary markers: The instructions do not specify boundary markers or directives to ignore instructions within the analyzed data.
- Capability inventory: The skill itself lacks executable capabilities; it only provides strategy guidelines for the agent's analysis.
- Sanitization: No sanitization methods are mentioned for the external content being analyzed.
Audit Metadata