linkfox-junglescout-keyword-share-of-voice
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes Amazon search result data (such as product titles and brand names), which constitutes untrusted external content.
- Ingestion points: Data enters the agent context through the response from the Jungle Scout API, triggered by the
keywordandmarketplaceparameters inscripts/junglescout_keyword_sov.py. - Boundary markers: The skill does not utilize specific delimiters or instructions to prevent the agent from following potential commands embedded in the search results.
- Capability inventory: The skill has the capability to perform network requests to
tool-gateway.linkfox.comand write data to the local project directory (linkfox/folder). - Sanitization: While the data is handled using standard JSON serialization, there is no evidence of filtering or sanitizing the content of external strings before they are processed by the agent.
- [COMMAND_EXECUTION]: The skill relies on the execution of Python scripts to perform its operations.
- The script
scripts/junglescout_keyword_sov.pyis used to query the SOV data and manage a local cache of the results. - The script
scripts/onboarding.pyprovides a CLI interface for users to log in, retrieve API keys, and manage their LinkFox account status.
Audit Metadata