slack
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses official developer domains (hyperfx-ai.ai) for integration setup and requirements.
- [NO_CODE]: No executable scripts or local code files are provided; the skill consists entirely of configuration and instructional content.
- [PROMPT_INJECTION]: The skill defines a control flow pattern using [NO_RESPONSE] to manage conversational noise in Slack channels, which is a benign instructional instruction.
- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it is designed to search and process external Slack message content.
- Ingestion points: slack_messages_search tool (referenced in SKILL.md).
- Boundary markers: No explicit boundary markers or 'ignore' instructions are provided for processing search results.
- Capability inventory: Writing and management capabilities including slack_messages_send, slack_files_upload, and slack_channels_create.
- Sanitization: No explicit content sanitization or instruction to ignore embedded commands is present.
Audit Metadata