why-did-this-post-flop
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a structured framework for diagnosing social media performance through natural language instructions. It does not contain executable scripts, hidden commands, or unauthorized network operations.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data, specifically social media post text and engagement metrics.
- Ingestion points: User-provided post content and performance statistics described in SKILL.md.
- Boundary markers: None explicitly defined in the instructions.
- Capability inventory: The skill is limited to providing analytical insights; it lacks high-risk capabilities such as file system access, shell execution, or external data exfiltration.
- Sanitization: No specific sanitization or filtering of input data is mentioned.
Audit Metadata