niche-tuner
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of natural language instructions within a Markdown file. No executable scripts, binaries, or automated workflows are present.
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access attempts were detected. The skill does not utilize any system tools, network capabilities, or file access.
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted input such as viewer comments and messages to extract keywords.
- Ingestion points: Step 2 directs the agent to analyze comments and DMs provided in the user's brief.
- Boundary markers: There are no explicit markers or instructions to ignore commands within the analyzed text.
- Capability inventory: The skill's scope is restricted to text generation. It lacks any capability to execute commands, write to the file system, or initiate network connections.
- Sanitization: No input sanitization is specified, but the lack of executable tools makes the processing of untrusted input a safe operation.
Audit Metadata