research-market
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from multiple external sources including web search results, social media posts, and RSS feeds.
- Ingestion points: Social listening and news fetching steps specified in SKILL.md and listening-craft.md.
- Boundary markers: While it mandates linking and quoting, it lacks robust delimitation or explicit warnings for the agent to ignore instructions embedded within the processed content.
- Capability inventory: The skill can write to the filesystem via gooseworks:file_write and schedule tasks using gooseworks:automation_upsert.
- Sanitization: The skill relies on the agent to manually verify quotes and numbers against source data without programmatic filtering.
- [COMMAND_EXECUTION]: The skill utilizes the gooseworks:automation_upsert tool to create and manage scheduled research tasks, which involves generating prompt templates for later execution.
Audit Metadata