channel-partnerships
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [PROMPT_INJECTION] (SAFE): The skill does not contain any instructions aimed at bypassing safety filters, overriding core behavior, or leaking system prompts.
- [DATA_EXFILTRATION] (SAFE): No network requests (curl, wget, etc.) or access to sensitive file paths (e.g., ~/.ssh, .env) were detected.
- [COMMAND_EXECUTION] (SAFE): This skill is entirely markdown-based and does not include any scripts or shell commands.
- [INDIRECT_PROMPT_INJECTION] (LOW): The skill is configured to ingest content from external reference files (
references/patterns.md,references/sharp_edges.md,references/validations.md). While this allows the agent to be influenced by data in those files, the skill lacks the write or network capabilities required to perform harmful side-effect actions. - [OBFUSCATION] (SAFE): No encoded strings, homoglyphs, or hidden Unicode characters were found in the file content.
Audit Metadata