threads-post
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and configuration files. It does not include any executable code, scripts, or commands that could compromise the host environment or the agent's safety.
- [SAFE]: No sensitive information, such as API keys, hardcoded credentials, or private file system paths, was identified. References to external services are standard for the intended social media management use case.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user instructions and external profile data to generate content. It mitigates potential injection risks by defining strict scope limitations and mandating content validation.
- Ingestion points: Accepts user prompts for post creation and reads external context from 'brand-profile' and 'goals-and-kpis' files.
- Boundary markers: Includes 'Honest scope' and 'Definition of done' sections that explicitly define what the skill can and cannot do.
- Capability inventory: Provides the agent with the ability to format and schedule posts for the Threads platform via the WoopSocial tool.
- Sanitization: Requires the agent to validate generated content against platform specifications and prohibits the use of algorithm-penalized tactics like engagement bait.
Audit Metadata