social-media-post-creator
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied 'essences' (notes, articles, bullet points) which creates a surface for indirect prompt injection.
- Ingestion points: The agent takes content from the user prompt as input for transformation (SKILL.md).
- Boundary markers: There are no explicit instructions or delimiters defined to separate user data from the agent's internal instructions.
- Capability inventory: The skill's capabilities are limited to text generation; no file system writes, network operations, or shell execution capabilities were detected in the skill instructions or reference files.
- Sanitization: There is no evidence of input validation or sanitization for the user-provided content.
Audit Metadata