keyword-research
Warn
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill's instructions guide the agent to execute local Python scripts (
suggest.py,firecrawl.py, andpageviews.py) using shell commands where user-provided inputs (seeds and keywords) are passed as arguments. This pattern presents a potential command injection vulnerability if the agent platform does not strictly sanitize or escape the user input before shell execution. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data from web search results and API services, creating an attack surface for indirect prompt injection.
- Ingestion points: Search results from Firecrawl sampling (Phase 5/6) and query data from the Search Console API (Phase 2).
- Boundary markers: The skill lacks explicit instructions for using delimiters or boundary markers to isolate external content from the core instructions.
- Capability inventory: The agent is authorized to write persistent data to the
memory/directory and execute scripts within the plugin root. - Sanitization: No sanitization or filtering logic is prescribed for the data retrieved from external search providers.
- [EXTERNAL_DOWNLOADS]: The skill facilitates data retrieval from several external sources including Google Autocomplete, the Firecrawl search service, and Wikipedia pageview metrics via its connector scripts. These are standard operations for the skill's stated purpose but involve fetching data from remote endpoints.
Audit Metadata