mmk-threads-replies
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were detected. The skill uses a vendor-specific tool (mmk) and restricts the agent's environment using the allowed-tools configuration in the frontmatter.
- [PROMPT_INJECTION]: The skill interacts with external content from Threads, creating a surface for indirect prompt injection (Category 8).
- Ingestion points: External data enters the agent's context through the output of the mmk threads replies command in SKILL.md.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the skill.
- Capability inventory: The agent's capabilities are restricted to the mmk tool suite via the Bash tool.
- Sanitization: No sanitization or validation of the retrieved Threads data is mentioned in the skill documentation.
Audit Metadata