ai-visibility-monitor
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes several local Python scripts, including
scripts/ai_visibility.py,scripts/dfs_client.py, andscripts/report_publish.py, to perform its core functions of checking brand visibility and publishing reports. These are standard operations for its stated purpose. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, such as AI assistant responses and search engine results, which acts as a potential surface for indirect prompt injection.
- Ingestion points: Mentions and excerpts gathered from ChatGPT, Claude, Gemini, and Google AI Overviews are ingested during visibility checks.
- Boundary markers: No explicit delimiters are mentioned to isolate untrusted data within the processing flow.
- Capability inventory: The skill possesses the capability to execute shell commands and write files to the local directory or a specified reports directory.
- Sanitization: The documentation does not specify sanitization or validation protocols for the external content retrieved from platform APIs.
Audit Metadata