channel-selection
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of markdown-based instructions for an AI agent to help users with marketing decisions. It does not utilize shell commands, tool calls, or network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an ingestion surface by instructing the agent to read from local state files such as .agents/marketing-learnings.md and .agents/marketing-strategy.md. While this allows external data to influence the agent's reasoning, the skill lacks the capabilities (such as file-writing or network access) to perform automated malicious actions. 1. Ingestion points: .agents/marketing-learnings.md and .agents/marketing-strategy.md (SKILL.md). 2. Boundary markers: No delimiters or ignore instructions are present for the ingested content. 3. Capability inventory: The skill is analytical only and does not invoke tools or shell commands. 4. Sanitization: There is no logic provided to sanitize or filter the content read from the files.
Audit Metadata